1.2 foss4g-na-2024 2024-09-09 2024-09-11 3 00:05 https://talks.staging.osgeo.org America/Chicago Purina Boardroom Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 QGIS has a Model Designer that allows to to graphically build processing tools to allow you to create/analyze/process data. This class will cover building tools with the Designer. foss4g-na-2024-2500-qgis-model-designer Use Case and Applications Randal Hale en This 3 hour class will cover building Processing tools using the Model Designer. Students will build custom tools to make repeatable tasks easier. Students will build models during class and will modify those models to make them more functional. Topics Covered: Introduction, Processing Tools, Model Designer, Building a Model, and Command Line functionality. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RTH9WP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RTH9WP/feedback/ Purina Boardroom Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 Learn design principles to make maps that communicate well. This workshop is divided into two sections. The first covers concepts and approaches to designing maps. The second will provide hands-on experience making a map in QGIS. foss4g-na-2024-2465-cartography-for-professional-quality-maps-in-qgis Use Case and Applications Michele Tobias en When you're flipping through a book or journal article, you probably look at the pictures first. In a presentation, you don’t read the text. You look at the pictures! It’s the same with websites. Because images draw our attention, they are an incredibly important tool for conveying the message of your text or presentation. But communicating clearly with maps requires a specific set of skills that is distinct from other forms of communication. Key Concepts: • Minimize. Keep only what's absolutely necessary. • Tell the Story. What do I want my reader to learn from this map? How does it support the claims I make in my text? What story should my map tell? • Communication. Does my map communicate well? In this workshop, we'll learn strategies and steps to take in making maps that not only look good but communicate well. We’ll learn approaches and guidelines for creating professional quality maps using QGIS and practice a workflow that can be applied to other graphical GIS programs or even non-map figures. This workshop is divided into two sections. The first covers concepts and approaches to designing maps. The second will provide hands-on experience making a map in QGIS. Participants are encouraged to bring examples from their own work for discussion. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/HLXJST/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/HLXJST/feedback/ Missouri S&T Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 In this workshop we will explore how to set up a geospatial data science environment, use that environment to create a well spread and balanced sample, and estimate canopy cover from data derived from STAC, OSM, and REST services. foss4g-na-2024-2594-environment-setup-and-predictive-modeling Use Case and Applications John Hogland en Remotely sensed data, newer technologies, and modeling frameworks are fundamentally changing the way in which we understand and manage resources. In this short course, we will discuss how to setup a data science processing environment using Conda, build that processing environment using basic user permissions, demonstrate how to acquire raster and vector data from STAC, OSM, and REST services, illustrate how to use those data to create a well spread and balanced sample, create an ensemble of KNN models, and finally depict spatially explicit estimates of mean canopy cover and modeling error, locally and within cloud services using opensource Jupyter Notebooks and Python. Our notebook and use case walks analysts through the basic steps needed to create a well spread and balanced sample, integrating field data with remotely sensed data using machine learning and Raster Tools, and further illustrate how analysts can standardize this type of workflow using open-source data streams and software. Workshop learning objectives include: 1) learning about environments, 2) learn multiple sample designs strategies, 3) learn how to access cloud-based data and services, 4) learn the advantages of a well spread and balanced sample, 5) create an ensemble of predictive models, and 6) explore how to use those models to depict mean and standard error estimates in a spatially explicit manner. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/7P3DXB/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/7P3DXB/feedback/ Missouri S&T Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 Learn how to create geospatial web applications using GRASS GIS, Actinia, and OpenPlains. During the workshop we will learn how to develop web application using OpenPlains. foss4g-na-2024-2468-developing-web-application-with-grass-gis Climate, Environment and Sustainability Vaclav (Vashek) PetrasCorey White en GRASS GIS is a powerful geocomputational engine that enables the development of complex geospatial models and analytical workflows. In the workshop, we will learn how to set up an actinia REST API instance for GRASS GIS, develop custom analytical models as process-chain templates, and create an OpenPlains web application. We will use GRASS GIS, Python, Docker, Insomnia, and Jupyter Notebooks during the workshop. Additionally, some background knowledge surrounding REST APIs and web development is recommended. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/8ZVTJP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/8ZVTJP/feedback/ Maryville Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 Join our workshop to master Re:Earth, a no-code platform transforming spatial and 3D data visualization. Gain hands-on experience, utilizing its features to elevate your projects, suitable for all skill levels and unlocking new visualization possibilities. foss4g-na-2024-2511-3d-geospatial-visualization-unleashed-a-no-code-re-earth-workshop State of Software ShogoHirasawa en Join us for an immersive workshop to explore the capabilities of Re:Earth, the revolutionary no-code, open-source WebGIS tool from Eukarya Inc., which is web-based and requires no download to use. This workshop is designed to transform the way you visualize spatial and 3D data. Re:Earth is not only versatile but also serves as the underlying system for the Japanese Government Digital Twin project "Plateau". With Re:Earth, you can effortlessly view, analyze, and share geographical data in a visually engaging and interactive manner—no coding skills required. During the session, you will master the fundamentals of Re:Earth and learn how to customize the platform to meet your specific data visualization needs. This workshop is perfect for anyone looking to delve into the world of geospatial data, from beginners to experienced users. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/PMRW3V/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/PMRW3V/feedback/ Maryville Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 An end-to-end workshop discussing how to use R to create data visualizations and neighborhood level spatial analysis within the healthcare domain. foss4g-na-2024-2515-intro-to-gis-using-r Use Case and Applications Andrew VinsonSamuel Affare en Social Determinants of Health (SDOH) in combination with the structural determinants of health are the social and physical conditions in which people are born, grow, live, work, play, and age. Given the spatial nature of the social determinants of health, mapping this data has long been crucial to epidemiologists, healthcare data scientists, researchers, and policy makers for identifying inequities and engaging in community-level efforts to prioritize community resources. With R, an open source programming language, it is possible to run reproducible end-to-end geo-computation ranging from feature engineering to spatial modelling to allow for more thorough investigation of geographic disparities between neighborhoods. Utilizing publicly available health data sources and the US census data, this tutorial will explore how to use R to create data visualizations and neighborhood level spatial analysis within the healthcare domain. This workshop will help healthcare data scientists, research and professionals develop stronger geo-computation and cartography skills. Module 1: Getting Started with Geospatial Data in R Module 2: Basic Cartography and Data Visualization Module 3: Spatial Interpolation and Feature Engineering Module 4: Spatial Clustering Module 5: Spatial Regression Requirements - Basic knowledge of R - Experience with Rstudio false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NAYPVV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NAYPVV/feedback/ Harris Stowe Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 Work with large-scale geospatial data by leveraging Apache Sedona for vector and raster data using Spatial SQL to perform spatial joins, zonal statistics, and raster inference with large datasets that wouldn't be possible on a single machine. foss4g-na-2024-2540-cloud-native-geospatial-analytics-with-apache-sedona William Lyon en This hands-on workshop will focus on using Apache Sedona for working with large-scale vector and raster data. We'll use Spatial SQL and Python to perform spatial joins, zonal statistics, and raster inference with large datasets that wouldn't be possible on a single machine. We'll also see how cloud-native data formats like GeoParquet, Cloud Optimized GeoTiffs, and Apache Iceberg can help accelerate geospatial data anlysis. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/BY7YLJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/BY7YLJ/feedback/ Harris Stowe Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 The workshop describes processes and tools used by the author and his team to build and consume digital twins for urban environments. Participants will gain exclusive insights into the development of digital twins to consume them within MapStore WebGIS framework foss4g-na-2024-2507-building-and-consuming-urban-digital-twins-with-open-source-tools Stefano Bovio en In an era where urban development demands innovative solutions, this workshop describes processes and tools used by the author and his team to build and consume digital twins for urban environments. Leveraging the latest advancements in open-source geospatial technology, we will guide attendees through the process of transforming vector data and point cloud datasets into 3D models using open-source tools in order to consume them within MapStore WebGIS framework (thanks to its support for Cesium JS) and consequently within the GeoNode platform. This hands-on session is designed around the implementation of pipelines and cutting-edge 3D visualization techniques, directly applicable to real-world urban contexts. Participants will gain exclusive insights into the development of digital twins, drawing upon our team's extensive experience with urban reconstruction projects. The workshop will showcase how these digital replicas serve as essential tools for urban planning, facilitating detailed analysis, scenario planning and public engagement. Attendees will be provided with sample data from a selected city in the US, offering a unique opportunity to learn skills to convert and visualize this data on the web using 3D Tiles format within a MapStore instance. This process not only demonstrates the conversion of geospatial data into 3D Tiles format ready to be served over the web but also underscores the importance of interoperability and accessibility in geospatial data management. Through this workshop, participants will: - Learn how to effectively convert vector (shapefiles) and point cloud (las) data into 3DTiles format compatible with MapStore and Cesium JS. - Explore the MapStore WebGIS application for enhanced 3D visualization and GIS capabilities using the generated 3D Tiles. - Get access to a docker artifact containing the tools presented during the webinar with sample data from the open data portal of Washington DC to replicate the process - Engage in hands-on exercises that illustrate the creation and utilization of 3D digital twins, from data conversion to visualization and analysis within a MapStore framework. This session is ideal for GIS professionals, urban planners, researchers, and anyone interested in the forefront of geospatial technology and urban development. A repository with a docker solution will be provided to the attendees to facilitate the setup of all needed tools. A basic understanding of python and javascript languages is needed even if most of the processes and interactions will be done with a dedicated user interface. Join us to explore how the synergy between MapStore, GeoNode and innovative 3D data processing can pave the way for smarter, more sustainable urban futures. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/E9H7RL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/E9H7RL/feedback/ South Classroom Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 pgRouting is a PostgreSQL extension that extends PostGIS extension for network routing. I am here, want to go there, how do I do it? This workshop will teach you the basics of using SQL for pedestrian and vehicle routing. foss4g-na-2024-2455-pgrouting-for-city-network-routing Use Case and Applications Vicky Vergara en pgRouting is a PostgreSQL extension that extends PostGIS extension for network routing. I am here, want to go there, how do I do it? This 3-hour hands-on workshop will teach you the basics of using SQL for pedestrian and vehicle routing. You'll learn how: - To upload data and prepare it for routing. - Use the data to route pedestrians and vehicles. - Interact with PostGIS to get information of the route. 1. Prepare Data 1.1. Prepare the database 1.2. Get the Workshop Data 1.3. Upload data to the database 1.4. Chapter: Appendix 2. Pedestrian Routing 2.1. pgr_dijkstra 2.2. pgr_dijkstraCost 3. Vehicle Routing 3.1. Routing for vehicles 3.2. Cost manipulations 4. SQL function 4.1. The application requirements 4.2. Preparing processing graphs 4.3. Geometry handling 4.4. Creating the Function false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZUW7H7/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZUW7H7/feedback/ South Classroom Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 Learn how to use PostGIS and it's family of extensions. How to load and query data (geometry, geography, raster). Time permitting we'll cover topology. foss4g-na-2024-2531-using-postgis Use Case and Applications Regina ObeLeo Hsu en Basics ==================== * Installing PostGIS * Overview of basic PostGIS types - geometry, geography, raster, topology Working with geometry and geography data ====================================== * Creating data with functions input functions * Loading data from various file formats * Using foreign data wrappers (ogr_fdw, postgres_fdw, file_fdw) * Viewing data in OpenJump, QGIS, and pgAdmin4 * Proximity Queries - find top 10 closest things, pois within a distance of me, * Geometric Processing - Buffers, Unions, and More * Geocoding using postgis_tiger_geocoder extension Advanced Topics (time permitting) ====================================== * Loading raster data with raster2pgsql * Using geometry and raster in single query * Using postgis_sfcgal extension for 3D operations * Using postgis_topology for data management false https://talks.staging.osgeo.org/foss4g-na-2024/talk/BM3LAN/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/BM3LAN/feedback/ Deloitte Conference Room Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 Get started with shiny new AI/ML! This workshop is hands on AI/ML vector data and use cases. Starting with unstructured data sets we will create vectors, put them in PostgreSQL, and then use pg_vector (and PostGIS) for analysis. foss4g-na-2024-2493-vector-dbs-and-why-should-geospatial-people-care Geo AI/ML Steve Pousty en The recent rise of “AI,” and its potential impact, has made it the focus of discussion (and hype). Vector databases play a vital role in this emerging area of technology. These databases can play a key role in your search and AI workflows. There are data stores built de novo, just for vector data and most of the major traditional data stores have added vector capabilities as well. This workshop is going to get you hands on with vector data and some use cases. You will be able to answer questions such as: What are these “vectors,” where do they come from, how do you query them, what are their use cases, and what role are they going to play in your existing infrastructure? We will look at some unstructured data sets, then look at their vectors, next put them in a vector store (PostgreSQL pg_vector), and finally do some fun and interesting queries. Bring your laptop and the ability to read Python code. If you are comfortable with Python, then you should be able to extend the code. Come get your hands dirty with this innovative technology, discuss its pros and cons, and get a sense of how to pick a starting vector database. Our vector database will be PostgreSQL with both PostGIS and pg_vector installed. Both of the datasets used in the examples come from open data set 1. https://alex.macrocosm.so/download 2. https://github.com/cvdfoundation/google-landmark The programming will be in Python and SQL. We will run it all using devcontainers running on GitHub. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/N9SAPN/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/N9SAPN/feedback/ Deloitte Conference Room Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 The workshop will provide an introduction to GeoNode starting with an overview of its functionalities for managing, data, users and documents covering also more advanced concepts. foss4g-na-2024-2504-introduction-to-geonode-the-open-source-geospatial-cms Giovanni AllegriEmanuele Tajariol en GeoNode is an open source web platform for the development of interoperable spatial data infrastructure. The software is designed to be easily extended, customized and integrated into existing systems. The workshop will provide an introduction to GeoNode starting with an overview of its functionalities for managing data, users and documents covering also more advanced concepts like managing layers, editing layer styles, managing maps and geostories and more; advanced information on data management will also be provided in order to ensure performance data dissemination. In order to participate no previous knowledge of GeoServer and OGC services is required, but a basic knowledge of GIS concepts and basic data formats (shapefiles, geotiff) is recommended. Participants should provide their own laptop with Docker installed and configured. Instructions in order to prepare the workshop here: https://github.com/geosolutions-it/geonode-workshop#readme As an alternative, a VirtualBox image pre-configured with GeoNode 4.2.3 is available here: https://tinyurl.com/geonode-423-ova Sample data that will be used within the workshop can be downloaded here: https://tinyurl.com/geonode-workshop-sample-data false https://talks.staging.osgeo.org/foss4g-na-2024/talk/WMZQFJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/WMZQFJ/feedback/ Holekamp Classroom Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 This workshop aims to bridge the gap between big geospatial data and research scientists by providing training on an open-source online platform for managing big drone and satellite data. foss4g-na-2024-2470-open-source-pipeline-to-integrate-drone-and-satellite-data Data Management and Interoperability Qiusheng WuJinha Jung en Recent advances in drone technology have revolutionized the remote sensing community by providing means to collect fine spatial and high temporal resolutions at affordable costs. As people are gaining access to increasingly larger volumes of drone and satellite geospatial data products, there is a growing need to extract relevant information from the vast amount of freely available geospatial data. However, the lack of specialized software packages tailored for processing such data makes it challenging to develop transdisciplinary research collaboration around them. This workshop aims to bridge the gap between big geospatial data and research scientists by providing training on an open-source online platform for managing big drone data known as Data to Science. Additionally, attendees will be introduced to powerful Python packages, namely Geemap and Leafmap, designed for the seamless integration and analysis of drone and satellite images in various applications. By participating in this workshop, attendees will acquire the skills necessary to efficiently search, visualize, and analyze geospatial data within a Jupyter environment, even with minimal coding experience. The workshop provides a hands-on learning experience through practical examples and interactive exercises, enabling participants to enhance their proficiency and gain valuable insights into leveraging geospatial data for various research purposes. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KHCG7R/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KHCG7R/feedback/ Holekamp Classroom Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 The PDAL Workshop https://pdal.io/en/latest/workshop/index.html teaches users common processing patterns of geospatial LiDAR point cloud data and shows you how to take advantage of PDAL's processing and orchestration capabilities through its Pipeline concept. foss4g-na-2024-2449-point-cloud-processing-and-analysis-with-pdal Michael SmithHoward Butler en See https://pdal.io/en/latest/workshop/index.html for a full description of the exercises and approach of the PDAL workshop. Attendees are encouraged to arrive with some of their own point cloud processing challenges. After a short lecture, participants will direct themselves through the workshop content with access to instructors for questions, hypotheticals, and discussion. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/SQ3H3H/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/SQ3H3H/feedback/ Sharptooth Boardroom Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 Do you work in government or need to distribute data to others? Do you want to lower your maintenance burden while increasing the data you share with the public and other organizations? Attend this hands-on workshop to learn how! foss4g-na-2024-2532-introduction-to-data-engineering FOSS4G in Government Daniel J. Dufour en Do you work in government or need to distribute data to others? Do you want to lower your maintenance burden while increasing the data you share with the public and other organizations? Attend this workshop to learn how you can use free open-source technology to build sustainable data pipelines. This workshop will be hands-on and you will actually build and deploy data pipelines during the workshop. We’ll go over the following: - Creating an open-source Github-based workflow using Github Actions - Pulling data from OpenStreetMap using Overpass Turbo - Setting up your development environment on Macos, Linux and/or Windows - How to automate pulling of data from a custom Google Map - Converting data using ogr2ogr (installed with GDAL) - Processing CSV files using csvkit - Reading Oracle Transaction Business Intelligence (OTBI) reports using open-source JavaScript - Publishing scheduled reports to your open data portal using open-source JavaScript run on Google Apps Script false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KFXGRM/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KFXGRM/feedback/ Sharptooth Boardroom Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 A step by step, hands-on guide to creating and using an extract of OpenStreetMap data, using tools like osmium, osm2pgsql, and QGIS. foss4g-na-2024-2459-your-very-own-osm-create-a-regional-extract-of-openstreetmap Open Data Joshua Carlson en OpenStreetMap is a global dataset with a wealth of data, just waiting for you to use it! Many organizations both large and small use OSM data in some capacity, and so can you! Whether you are a lone cartographer looking for basemap details for your next creation or a GIS developer building your organization new tools, OpenStreetMap can probably fit into your project. Being free and open source, there are few barriers between wanting OSM and actually getting it. But to the unfamiliar, it can be a little daunting knowing where to start. That's where this workshop comes in. Workshop participants will be guided through a basic workflow of downloading OSM data, creating a geographic subset, loading desired features into a database, and accessing the imported data through QGIS. And of course, the entire process will be done with free, open-source software! false https://talks.staging.osgeo.org/foss4g-na-2024/talk/898CLY/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/898CLY/feedback/ Anheuser-Busch Pre-Conference Workshop 2024-09-09T09:00:00-05:00 09:00 03:00 This workshop introduces OGC APIs, their story, objectives and structure, with practical examples from the GeoServer implementation. Join this workshop to get an update on the APIs, learn the current implementation progress, and discover some GeoServer unique features too. foss4g-na-2024-2549-ogc-apis-an-introduction-with-geoserver Andrea Aime en GeoServer is a web service for publishing your geospatial data using industry standards for vector, raster and mapping. It powers a number of open source projects like GeoNode and geOrchestra and it is widely used throughout the world by organizations to manage and disseminate data at scale. This workshop will get your started with OGC APIs, and their implementation in GeoServer, covering: * An introduction to the common concepts in OGC APIs * The landing page of a service * The OpenAPI definition of a service * OGC API Features, the schemaless, vector data access service * OGC API Styles, or how to access styles and eventually apply them client side * OGC API Tiles, or how to get tiled data and images * OGC API Map, or how to get maps in a given area and projection * OGC API Coverages, downloading raw raster data GeoSolutions will make available an all-in-one package to run the workshop as a VM for VirtualBox or a self-contained Zip file for Windows. This should be pre-installed on attendees' laptops before the workshop. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/LJ3AAS/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/LJ3AAS/feedback/ Anheuser-Busch Pre-Conference Workshop 2024-09-09T13:00:00-05:00 13:00 03:00 Learn how to build and serve vector tiles with GeoServer, and how GeoServer can be well suited to mixed serving use cases (raster + vector), dynamic data, as well as handling different views based on the current user security clearance. foss4g-na-2024-2561-vector-tiles-with-geoserver Use Case and Applications Andrea Aime en GeoServer is well known for its wide support for classic OGC services. But does it handle vector tiles? Yes, it does, but dealing with the assumptions of the XYZ ecosystem requires some simple preparations. The set up of the scale dependencies and data sources may also be new to those already used to vector tiles, while it comes more naturally to those having a OGC service background. Join this workshop to learn basics about vector tiles, their usage, the performance factors, how to setup GeoServer for painless usage, and how to use vector tiles with the tools in the XYZ ecosystem. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/PGGVHV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/PGGVHV/feedback/ Grand A Talk 2024-09-10T10:30:00-05:00 10:30 00:30 This presentation will introduce the attendees to the capabilities of the latest version of GeoNode and to some practical use cases of particular interest in order to also highlight the possibility of customization and integration. foss4g-na-2024-2503-state-of-geonode State of Software Giovanni AllegriEmanuele Tajariol en The presentation covers the latest news about GeoNode, particularly the new features in GeoNode 4.3.0. They include upgrading to the latest version of MapStore and integrating all the plugins it provides. The news targets end-users developers and DevOps, since new front-end tools, APIs and services will be covered. Use cases will be presented during the talk to showcase applications of the new features. The conclusion will present planned and ongoing activities for the next releases, including a deeper integration of 3D Tiles publishing, the refactoring and enhancements to metadata models and editing, and much more. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/LEHF7R/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/LEHF7R/feedback/ Grand A Talk 2024-09-10T11:00:00-05:00 11:00 00:30 GeoServer is an open source project for publishing and processing geospatial data using standard protocols. This presentation updates the community on new features in releases 2.25 and 2.26. Join us to learn about this popular OSGeo project. foss4g-na-2024-2552-state-of-geoserver State of Software Andrea Aime en GeoServer is a web service for publishing your geospatial data using industry standards for vector, raster and mapping, as well as to process data, either in batch or on the fly. GeoServer powers a number of open source projects like GeoNode and geOrchestra and it is widely used throughout the world by organizations to manage, disseminate and analyze data at scale. This presentation provides an update on our community as well as reviews of the new and noteworthy features for the latest releases. In particular, we will showcase new features landed in 2.25 and 2.26 (to be released in September 2024). Attend this talk for a cheerful update on what is happening with this popular OSGeo project, whether you are an expert user, a developer, or simply curious what GeoServer can do for you. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ETRNMH/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ETRNMH/feedback/ Grand A Talk 2024-09-10T11:30:00-05:00 11:30 00:30 The OGC APIs offer modern, flexible geo-spatial services based on OpenAPI/RESTful principles. They feature a small core with extensions, JSON-first data, support for data tiles, specialized APIs, and extensibility. This presentation covers their development and GeoServer implementations. foss4g-na-2024-2553-demystifing-ogc-apis-with-geoserver-introduction-and-status-of-implementation Use Case and Applications Andrea Aime en The OGC APIs are a fresh take at doing geo-spatial APIs, based on WEB API concepts and modern formats, including: * Small core with basic functionality, extra functionality provided by extensions * OpenAPI/RESTful based * JSON first, while still allowing to provide data in other formats * No mandate to publish schemas for data * Improved support for data tiles (e.g., vector tiles) * Specialized APIs in addition to general ones (e.g., DAPA vs OGC API - Processes) * Full blown services, building blocks, and ease of extensibility This presentation will provide an introduction to various OGC APIs and extensions, such as Features, Styles, Maps and Tiles, STAC and CQL2 filtering. Some have reached a final release, some are in draft: we will discuss their trajectory towards official status, as well as how good the GeoServer implementation is tracking them, and show examples based on the GeoServer HTML representation of the various resources. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NFGXRV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NFGXRV/feedback/ Grand A Talk 2024-09-10T13:00:00-05:00 13:00 00:30 Discover how GeoServer manages, locates, and displays vast satellite imagery collections from missions like Landsat and Sentinels. Learn about indexing, efficient image management with Cloud Optimized GeoTIFFs, visualizing mosaics, extracting imagery, generating animations, and performing band algebra operations. foss4g-na-2024-2560-earth-observation-data-with-geoserver-cog-stac-opensearch-and-more Data Management and Interoperability Andrea Aime en Never before have we had such a rich collection of satellite imagery available to both companies and the general public. Between missions such as Landsat 8 and Sentinels and the explosion of cubesats, as well as the free availability of worldwide data from the European Copernicus program and from Drones, a veritable flood of data is made available for everyday usage. Managing, locating and displaying such a large volume of satellite images can be challenging. Join this presentation to learn how GeoServer can help with with that job, with real world examples, including: * Indexing and locating images using The OpenSearch for EO and STAC protocols * Managing large volumes of satellite images, in an efficient and cost effective way, using Cloud Optimized GeoTIFFs. * Visualize mosaics of images, creating composite with the right set of views (filtering), in the desired stacking order (color on top, most recent on top, less cloudy on top, your choice) * Perform both small and large extractions of imagery using the WCS and WPS protocols * Generate and view time based animations of the above mosaics, in a period of interest * Perform band algebra operations using Jiffle Attend this talk to get a good update on the latest GeoServer capabilities in the Earth Observation field. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/CD7JHG/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/CD7JHG/feedback/ Grand A Talk 2024-09-10T13:30:00-05:00 13:30 00:30 Raster Attribute Tables are a way to attach a full set of attributes to raster data, giving rasters some of the vector data abilities. Come and learn how to use, mosaic and style and query RATs! foss4g-na-2024-2558-raster-attribute-tables-in-geoserver Image Processing Andrea Aime en Raster Attribute Tables (RATs) is a functionality that originated in GDAL several years ago, but that is not well known in the wild. RATs allow to attach a full set of attributes to image pixels, and then use them to perform rich querying, but also to support multiple legends and colormaps. GeoServer added support for RATs in recent versions, with interesting abilities to generate styles out of them, see all of the attributes in GetFeatureInfo outputs, and probably unique, mosaic files with different RATs into a single seamless output. Join this presentation to learn about the concept, its usage and the development challenges found in GeoServer as we have faced a Raster Attribute Table with more than 30 thousand entries! false https://talks.staging.osgeo.org/foss4g-na-2024/talk/8VZLY3/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/8VZLY3/feedback/ Grand A Talk 2024-09-10T14:00:00-05:00 14:00 00:30 The emerging draft OGC API - Connected Systems Standard enables interoperability among sensors, things, robots, drones, satellites, control systems and platforms across space, air, land, sea, cyber, and electromagnetic domains. This session will introduce open source software implementation that support it. foss4g-na-2024-2670-open-source-implementations-of-the-ogc-api-connected-systems-standard Data Management and Interoperability Christopher Tucker en The emerging draft OGC API - Connected Systems Standard enables interoperability among sensors, things, robots, drones, satellites, control systems and platforms across space, air, land, sea, cyber, and electromagnetic domains. This session will introduce several open source software implementation that support it. This new standard represents the modernization of the OGC Sensor Web Enablement (SWE) standards, implementing OpenAPI/REST/JSON patterns, as well as realtime streaming and asynchronous Pub/Sub mechanisms. The OGC API - Connected Systems Standard enables the discovery, access, storage/management, processing, reasoning, visualization, tasking and action of/by these various kinds of sensing systems. This covers everything from accessing simple IoT or sensor data to tasking satellites and autonomous UxS platforms, and everything in between. This standard brings a new alignment with the OGC API - Features specification in the OGC API - Connected Systems - Part 1, allowing open source clients capable of this foundational OGC specification to access static representations of observations from sensing systems. This new bridge between the OGC mapping world and the OGC SensorWeb brings a new level of interoperability to sensor data within geospatial mapping applications. OGC API - Connected Systems - Part 2 is designed to deal with dynamic Data Streams of Observations and Control Streams of Commands. These are built on the the modernization of SensorML and SWE Common, now providing JSON encodings, in SensorML 3.0 and SWE Common 3.0. This new standard is already supported in OpenSensorHub (www.OpenSensorHub.org), osh-js, OWSLib (https://www.osgeo.org/projects/owslib/), and 52 North (https://52north.org/), with other open source libraries under development for both servers and clients. Client implementations in Python, C++, Java, and Go should be in motion by the time of this FOSS4G-NA presentation. Pathways toward an OGC API - Connected Systems QGIS plugin will also be discussed. The goal is to have broad based language support for the OGC API - Connected Systems Standard before the end of 2024, enabling a wide range of developers in their language of choice. The goal is also to enable legacy/heritage systems written in different kinds of languages to more easily support the new standard without fundamentally changing their systems. Open source OSH/SensorML Drivers have been developed for a wide variety of sensing systems, with 25 technical use cases with live demo services available for developers to begin testing their own clients and servers. These are outlined in detail in a 120 page Reviewers Guide (OGC API - Connected Systems Standard Reviewers Guide_DRAFT) along with a detailed lay-accessible discussion of the standard itself. It is the intent of this presentation to make it very easy for traditional FOSS4G developers to begin incorporating real-time dynamic data from all manner of sensing systems into their geospatial applications, whether based on OpenLayers, Leaflet, Mapbox, Cesium, Esri, TAK, or their own favorite web mapping framework. Ease of integration and adoption is a major focus of the presentation, with a focus on developer resources in different languages. NOTE: The emerging draft OGC - API Connected Systems Standard may have completed its final global vote by the time of presentation. As of the time of submission, this draft standard is under review by the OGC Architecture Board, which will vote out the standard for global public review within the month of July. We expect that the 30 day public review will result in a final vote in August. Package submitted OGC API - Connected Systems - Part 1: https://docs.ogc.org/DRAFTS/23-001r0.html, OpenAPI doc OGC API - Connected Systems - Part 2: https://docs.ogc.org/DRAFTS/23-002r0.html, OpenAPI doc SensorML 3.0: https://docs.ogc.org/DRAFTS/23-000.html SWE Common 3.0: https://docs.ogc.org/DRAFTS/24-014.html These will be quickly followed by the submission of the additional Part 3 (Pub/Sub), 4 (Sampling Features) and 5 (Binary Encoding Formats). The draft standard is available on GitHub (https://github.com/opengeospatial/ogcapi-connected-systems) and outlines the 5 parts in the following manner: Part 1 - Feature Resources (Current Draft Preview, OpenAPI Docs) Systems (metadata of sensors, actuators, platforms, simulations, etc.) Procedures (metadata of procedures implemented by system, which includes automated system specs/datasheets and human driven activities) Deployments (metadata of system deployments) Sampling Features (metadata about sampling geometries/methodologies used by observing systems) Subsystems / Components Property Definitions (semantical information for observed properties, controlled properties and system properties) Part 2 - Dynamic Data (Current Draft Preview, OpenAPI Docs) Dynamic Feature Properties Data Streams Observations Control Streams Commands and Command Status System Events Part 3 - Pub/Sub (AsyncAPI Docs) MQTT Bindings AMQP Bindings Part 4 - Sampling Feature Types OMS Sample Types (SpatialSample, StatisticalSample, MaterialSample) Feature Parts Parametric Sampling Features Part 5 - Binary Encoding Formats FlatGeobuf Encoding (for features) FlatBuffers Encoding (for obs and commands) Protobuf Encoding (for obs and commands) Common Video Formats false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KHCLXW/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KHCLXW/feedback/ Grand A Talk 2024-09-10T15:00:00-05:00 15:00 00:30 Learn how GRASS GIS users are efficiently processing, modeling, and analyzing big geospatial data locally, on the cloud, and on high performance computing clusters (HPC). foss4g-na-2024-2525-grass-gis-as-geocomputational-engine Use Case and Applications Vaclav (Vashek) PetrasCorey White en This talk will cover how users currently use GRASS GIS as their geocomputational engine. We will cover how GRASS GIS can be utilized locally, on the cloud, and in high-performance computing (HPC) clusters. We will highlight specific use cases to demonstrate what technologies and problems GRASS GIS users are solving worldwide. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/7JZHV3/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/7JZHV3/feedback/ Grand A Talk 2024-09-10T15:30:00-05:00 15:30 00:30 Learn about the latest advancements in GRASS GIS and what is coming next! Current feature overview included. foss4g-na-2024-2528-state-of-grass-gis State of Software Vaclav (Vashek) PetrasCorey White en GRASS GIS provides users with a large number of geospatial modeling, analysis, and data management tools. The software comes with a Python API, CLI, and graphical user interface, with additional APIs available for C and R. Faster release cycle now brings larger updates to users every year. In this talk, we will highlight what’s new in version 8.4 and discuss the greater GRASS GIS ecosystem and project roadmap. We will cover the most important tools available and will highlight tools even current users may not know about. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NF8C73/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NF8C73/feedback/ Grand A Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 QGIS-US Meeting foss4g-na-2024-2951-qgis-birds-of-a-feather Use Case and Applications Randal Hale en HEY - you want to talk about QGIS? You want to know the good/bad/ugly with QGIS-US? It's time to get active so I'm going to be talking about QGIS-us and lets get the US Community moving! false https://talks.staging.osgeo.org/foss4g-na-2024/talk/YZDNBP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/YZDNBP/feedback/ Grand B Talk 2024-09-10T10:30:00-05:00 10:30 00:30 What does it mean to be cloud-native in the context of geospatial data? This talk will cover how to leverage scalable compute and cloud-native data formats for high performance and large-scale geospatial analytics with Apache Sedona. foss4g-na-2024-2548-cloud-native-spatial-intelligence-with-apache-sedona Use Case and Applications William Lyon en This talk will cover the architecture and benefits of the open-source Apache Sedona project including use cases for gaining insights from geospatial data at scale such as raster data analysis like zonal statistics, spatial joins, and applying machine learning to satellite imagery with raster inference. We discuss the challenges that can arise when working with geospatial data at scale and Apache Sedona is architected to address these challenges. Finally, we examine how leveraging cloud-native data formats like GeoParquet and Apache Iceberg can enable large-scale geospatial analytics. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/N3HHVV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/N3HHVV/feedback/ Grand B Talk 2024-09-10T11:00:00-05:00 11:00 00:30 You'll learn tricks that leverage the power of PostGIS and combine with unique features PostgreSQL as well as other PostgreSQL extensions. foss4g-na-2024-2620-postgis-unleashed Use Case and Applications Regina Obe en PostGIS + PostgreSQL is one of the most popular spatial databases out there. In this presentation you'll learn why PostGIS beats out the competition by leveraging features unique to PostgreSQL that no other relational database has and what other extensions you can use in conjunction with PostGIS extensions to add that extra fire. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/APLY9D/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/APLY9D/feedback/ Grand B Talk 2024-09-10T11:30:00-05:00 11:30 00:30 PostGIS forms the backbone of many open-source geospatial projects. I’ll help you get started with managing Postgres outside of your local machine. We’ll cover hosting, sizing, tuning, backups, connections, and basic performance topics to get you started. foss4g-na-2024-2482-postgres-and-postgis-ops-management Data Management and Interoperability Elizabeth Christensen en Topics covered (in brief): Postgres hosting options: self-hosted, cloud, Kubernetes, local options Fully managed choices and self managed Storage & backups, backup files vs backup systems Postgres memory, sizing and tuning How I/O works Roles and role groups Connections for applications Introduce indexes Monitoring options false https://talks.staging.osgeo.org/foss4g-na-2024/talk/978LPP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/978LPP/feedback/ Grand B Talk 2024-09-10T13:00:00-05:00 13:00 00:30 Pg_featureserv and pg_tileserv are lightweight Go applications for getting your spatial data into web apps. This will be an introductory talk on how to set up these tools, use the sample code, and build your own spatial web maps. foss4g-na-2024-2484-web-maps-from-postgis-with-pgfeatureserv-and-pgtileserv Use Case and Applications Elizabeth Christensen en TOC Show a sample PostGIS database Set up local copy of pg_featureserv and pg_tileserv Show URL calls and how the CQL works Demo of web maps Demo pg_featureserv with pgRouting with click operations false https://talks.staging.osgeo.org/foss4g-na-2024/talk/AAWH87/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/AAWH87/feedback/ Grand B Talk 2024-09-10T13:30:00-05:00 13:30 00:30 You'll learn what pgRouting is and how you can prep your data and use it to solve various network routing problems. foss4g-na-2024-2619-pgrouting-an-introduction Use Case and Applications Leo Hsu en You'll learn what pgRouting is and how you can prep your data and use it to solve various network routing problems. We'll be using St. Louis data for this fast paced talk. Key take aways: * What is pgRouting and terminology used * How to prep data for routing * Various routing algorithms to do Point to Point, Trip Planning, computing service areas false https://talks.staging.osgeo.org/foss4g-na-2024/talk/EEKNA8/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/EEKNA8/feedback/ Grand B Talk 2024-09-10T14:00:00-05:00 14:00 00:30 pgRouting, the routing engine, can be used in different applications other than routing. foss4g-na-2024-2456-pgrouting-state-of-the-project State of Software Vicky Vergara en The UN OpenGIS initiative along with OSGeo Foundation organized the OSGeo UN Committee Educational Challenge where Challenge 2 was to create Workshop material for pgRouting. The challenge supports the objectives of the OSGeo UN Committee, i.e. promoting the development and use of open-source software that meets UN needs and supports the aims of the UN. pgRouting is not only useful for routing cars on roads but it can also be used to analyze water distribution networks, river flow or the connectivity of an electricity network, etc. Currently, this presentation talks about pgRouting addressing one of the Seventeen Sustainable Development Goals of the UN. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/FA79GJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/FA79GJ/feedback/ Grand B Talk 2024-09-10T15:00:00-05:00 15:00 00:30 DuckDB is a fast, open-source analytical SQL database that's gaining popularity. Discover how it can perform H3 operations on data quicker than other solutions. foss4g-na-2024-2655-blazing-fast-geospatial-sql-in-duckdb State of Software Isaac Brodsky en DuckDB is a fast, in-process, analytical open source SQL database engine. Isaac maintains the open source H3 hexagonal grid system and the bindings for H3 to DuckDB. In this talk, Isaac will cover why users may choose H3 on DuckDB for ease of use and performance. Highlights of the talk can include: * Why DuckDB is fast and gaining popularity. How DuckDB fits into the cloud-native application architecture at edge computing (serverless) and in the browser (WASM). * Ways to quickly get started with DuckDB locally using open datasets like Overture. DuckDB is a recommended way to read huge cloud optimized Parquet datasets like Overture. DuckDB runs locally and even in your browser. * Evolution of the DuckDB extension ecosystem, and how it has become easier to install and load open source extensions. Extensions can extend DuckDB with new capabilities, with more flexibility than cloud databases thanks to DuckDB being open source and local. * How to use the H3-DuckDB extension to perform geospatial operations. Will touch on why a user may want to choose the H3 hexagonal grid system, and how to write common geospatial operations in SQL. * Performance comparison with other approaches -- DuckDB SQL is much faster than Python or JavaScript calls. The H3-DuckDB bindings are set up for performance-by-default. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/YQWMQS/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/YQWMQS/feedback/ Grand B Talk 2024-09-10T15:30:00-05:00 15:30 00:30 RelateNG is a new algorithm for evaluating spatial relationships developed for the JTS/GEOS geoprocessing ecosystem. It offers many improvements in functionality, robustness, and performance. foss4g-na-2024-2478-faster-better-spatial-relationship-evaluation-with-relateng State of Software Martin Davis en Evaluating spatial relationships (such as intersects and contains) is likely the most common operation performed in geoprocessing. Many systems implement the Dimensionally-Extended 9 Intersection Model as defined in the OGC Simple Features specification. A large number of those systems use the JTS and GEOS geometry libraries, which have provided full-featured support for DE-9IM spatial relationships since their inception. Recently a new JTS/GEOS algorithm called RelateNG has been developed. It offers significant improvements in functionality, robustness, and performance. This talk gives an overview of spatial relationship evaluation, some challenges in implementing them, and describes the design and capabilities of the RelateNG algorithm. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KNGCFA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KNGCFA/feedback/ Grand B Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 If you love Structure Query Language (SQL), then you'll love Spatial SQL. What is Spatial SQL? It's SQL with an extra spatial sauce. Pretty much any database that speaks SQL, can speak Spatial SQL as well. foss4g-na-2024-2952-spatial-sql-birds-of-a-feather Data Management and Interoperability Regina Obe en If you love Structured Query Language (SQL), then you'll love Spatial SQL. What is Spatial SQL? it's SQL with an extra spatial sauce. Pretty much any database that speaks SQL, speaks Spatial SQL as well. Most of these databases speak Spatial SQL that is a subset or superset of the ISO SQL Multi-Media Standard Part 3 (SQL/MM Spatial). Whether you are new to SQL or a long time lover, come join us as we discuss how you can avoid writing 1000s of lines of code, with just one Spatial SQL statement and how you can use similar Spatial SQL statements in countless FOSS4G tools - PostgreSQL (with PostGIS, pgRouting and other spatial extensions), Apache Sedona, DuckDB, and more. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZJHYVS/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZJHYVS/feedback/ Grand C Talk 2024-09-10T10:30:00-05:00 10:30 00:30 Raster Tools easily scales across various hardware configurations and lowers the barriers for parallel processing for spatial, statistical, and machine learning procedures; further advancing researchers’ and practitioners’ abilities to transform data into useful information for decision making. foss4g-na-2024-2518-transforming-data-into-useful-information-for-natural-resource-decision-making Use Case and Applications John Hogland en Big data and the knowledge we glean from it are fundamentally changing the way resource management decisions are made. The use of remotely sensed data, ever expanding computer technology, and enhanced processing techniques provide natural resource managers with depictions of ecosystems at unprecedented spatial and temporal resolutions. While these sources of information are currently being leveraged to inform decision making, the sheer amount of data currently being collected has outpaced our abilities to efficiently manipulate and use those data for decision making. Newer tools, algorithms, and approaches are needed to address processing limitations and provide new opportunities to embrace the volume, variety, and velocity of big data streams. Important questions related to data scale, relevance, transformation , as well as the types of tools needed to efficiently extract information for decision making are at the forefront of empirically driven decision making . To that end we have developed a python based geospatial processing library called Raster Tools that automates delayed reading and parallel processing. In this presentation, we highlight two case studies that use the newly developed Raster Tools package to perform spatial, statistical, and machine learning analyses. The first case study uses Raster Tools, basal area ha-1, stem counts ha-1, and forest cover type raster surfaces to inform sample design and improve variable estimation for forest stand inventories within the Fort Stewart significant geographic area (SGA) located in Georgia, USA. While the raster surfaces provide useful information for prioritizing longleaf pine (Pinus palustris) restoration efforts, timber sale administrators will want to know the volume or weight of the merchantable timber within the stands identified for treatment prior to implementation. Estimating existing volume for various timber products across a forest can be expensive. To reduce the cost of volume estimation, timber sale administrators can use ancillary data that are highly correlated with volume data to substantially reduce sampling effort for a given level of estimation accuracy. To illustrate these concepts, we will present a Jupyter notebook that demonstrates how Raster Tools can be used to both identify restoration sites and summarize basal area data used to aid in planning a sample design that reduces inventory costs and estimation error. The second case study uses Raster Tools and raster surfaces depicting basal area ha-1, stem counts ha-1, and spatially explicit error estimates to identify and prioritize longleaf gopher tortoise habitat restoration in Florida, USA. This example highlights the flexibility and efficiencies of Raster Tools, how Raster Tools can be integrated with conventional raster spatial modeling, and the use of fine grained spatially explicit information to aid in habitat restoration. Three key components to this example are 1) spatially defining existing and potential open pine gopher tortoise habitat, 2) evaluating the use of prescribed fire within existing and potential gopher tortoise habitat, and 3) integrating recreational aspects into the prioritization process. Like the previous use case, we will present a Jupyter notebook that demonstrates the utility of Raster Tools in prioritizing gopher tortoise habitat restoration. At the forefront of this accelerated pace and scale of data driven decision making is the development of spatial, statistical, and machine learning techniques that fully leverage existing hardware and adopt newer processing strategies to integrate big data sources seamlessly and easily with the decision-making process. Packages such as Raster Tools facilitate this integration while also providing functionality that can be used to further our understanding of natural resources while simultaneously providing the computational framework to optimize and justify management decisions at both scale and extent. While these tools facilitate Big Data analytics, they also necessitate a broader understanding of the role of spatial data and analyses within decision making. Moreover, they highlight the need for easy access to and integration with various open source and proprietary software systems. Raster Tools provides a great deal of flexibility and is available through Python’s package index. These tools are readily available, free, and provide the fundamental architecture to ingest big data streams directly into spatial, statistical, and machine learning analyses. Moreover, these tools are easy to use and can facilitate data driven decision making at fine scale across broad extents. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/MQ7D3C/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/MQ7D3C/feedback/ Grand C Talk 2024-09-10T11:00:00-05:00 11:00 00:30 stac-rs is a Rust implementation of the SpatioTemporal Asset Catalog (STAC) specification. Our high-performance STAC tools include a STAC API server with duck-db and postgres backends, and our applications leverage latest developments in geoparquet and geoarrow. foss4g-na-2024-2551-stac-rs-high-performance-reliable-stac-tooling-with-rust State of Software Pete Gadomski en The SpatioTemporal Asset Catalog (STAC) community specification is a key component of the growing cloud-native geospatial ecosystem. Well built, spec-specific tooling is a key part of the community-supported software landscape, as it helps developers and data consumers alike work efficiently with the data they need without needing to deeply understand the spec or implement the tooling themselves. We present [**stac-rs**](https://github.com/stac-utils/stac-rs), a Rust implementation of the STAC spec, as part of the cloud-native geospatial software landscape. **stac-rs** includes: - A STAC API server with **duck-db** and **pgstac** backends - A command-line interface (CLI) for querying STAC APIs and static STAC catalogs - Several Rust libraries for building your own applications In this talk, we walk through the components of **stac-rs**, describe some of the advantages and disadvantages of a Rust implementation of the STAC spec, and provide some performance benchmarks against other widely used tooling (e.g. **stac-fastapi** and **stac-server**). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/XKKRJB/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/XKKRJB/feedback/ Grand C Talk 2024-09-10T11:30:00-05:00 11:30 00:30 KnowSTAC is a framework for creating dynamic STAC indexes that organize data not according to how they are published as collections or catalogs, but according to on-demand queries that can crosscut domains and organizations for improved collaboration. foss4g-na-2024-2547-knowstac-framework-for-creating-dynamic-and-knowledge-interoperable-stac-indexes Data Management and Interoperability Nathan McEachen en KnowSTAC is a framework for creating dynamic SpatioTemporal Asset (STAC) indexes that organize data not according to how they are published as collections or catalogs, but according to on-demand, user-defined and ad-hoc queries that can crosscut domains and organizations. Collections can be dynamically created and shared according to semantic classification, location (including hierarchies and spatial knowledge graphs), and time so that they can be discoverable for collaboration. For example, the results of a dynamic search including geological classification, vegetation, platform, sensor type, organizational hierarchy, geographic hierarchy, and/or temporal validity collectively might represent an answer to a question that, by making discoverable, could be incorporated into other collections to answer new questions. KnowSTAC is being developed for GeoPlatform.gov to support the national spatial data infrastructure (NSDI) mandate and to explore transitions to a geospatial knowledge infrastructure (GKI). SDIs are supplier-driven data networks, traditional data analytics, and services that are single direction and created for a general market. They are not sophisticated enough to allow for processing random, unpredictable, and context-dependent queries across multiple domains. A GKI is a knowledge-sharing paradigm that is client-driven by on-demand questions of individuals and the relationships between those questions across domains. Rather than publishing data, a move beyond SDI to GKI enables answers to be published that are interoperable with other questions. Our GKI approach involves using spatial knowledge graphs and ontology registries to facilitate semantic interoperability. Ultimately, our aim is to enable interoperability across different technologies. For example, the results of a STAC index query should be available in RDF so that their relationship with other spatial knowledge graphs can be discoverable using GeoSPARQL or used to bring geospatial awareness to Large Language Models. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TREZPD/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TREZPD/feedback/ Grand C Talk 2024-09-10T13:00:00-05:00 13:00 00:30 The STAC render extension offers a flexible schema for managing dynamic tiling rendering metadata. Come discuss how the NASA VEDA (Visualization, Exploration and Data Analysis) open science platform has used the render extension to simplify front end visualization. foss4g-na-2024-2576-on-the-fly-raster-visualizations-leveraging-stac-metadata-standards Image Processing Chuck DanielsHanbyul Jo en Dynamic tiling of raster data offers the benefit of on the fly access and transformation of static cloud native files that can then be visualized on a map. Development Seed's titiler is one such example of a dynamic tiling server capable of creating tiled mosaics from Cloud Optimized GeoTiffs (COGs). Rescaling, applying a colormap or band arithmetic for example are all possible by passing certain metadata as path parameters to a tiling endpoint. Storing these parameters is helpful for front end applications and clients may have custom application logic for dealing with dynamic tiling parameters. When working with a large number of datasets, this makes it cumbersome to manage the dynamic tile rendering metadata with the datasets themselves. In the STAC ecosystem we've proposed and implemented the [render extension](https://github.com/stac-extensions/render) that offers a flexible schema for managing dynamic tiling rendering metadata. STAC Collections or Items may include custom rendering metadata that can be used by a client to visualize the dataset where these parameters are needed. The extension was implemented in NASA's VEDA (Visualization, Exploration and Data Analysis) open science platform and allowed the creation of dynamic thumbnails and visualization of STAC Items. It also allowed the offloading of dataset specific metadata from the frontend application code base to the STAC Catalog. The tighter coupling of the render parameters with other dataset metadata via STAC greatly reduces the effort in managing those parameters in front end application logic and minimizes data inconsistencies. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/93BQN7/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/93BQN7/feedback/ Grand C Talk 2024-09-10T13:30:00-05:00 13:30 00:30 In recent years, STAC has become crucial for geospatial data interoperability, particularly for indexing public datasets. This presentation will provide an update on STAC and highlight the largest public implementations: Earth Search (AWS), Planetary Computer (Azure), and CMR-STAC (NASA). foss4g-na-2024-2562-stac-for-public-eo-data Data Management and Interoperability Matthew Hanson en The STAC spec, and open-source software ecosystem around it, has provided an interoperable standard for access to geospatial data. This is most apparent with large public datasets that have been made available through different cloud providers. However, the data collections and metadata surfaced through these different APIs is different. This presentation will provide a brief update on the STAC specification itself, the changes with STAC 1.1, and the state of the extensions and ecosystem. It will also include an overview of the major public catalogs with an emphasis on Earth Search. Earth-Search provides an index for some public datasets available through the AWS Registry of Open Data (RODA) and has been shown to be a valuable resource for accessing the Sentinel-2 archive as Cloud-Optimized GeoTIFFs and is being used by researchers for science and commercial companies for building applications. We will present recent updates to Earth Search and will explain the differences between the different Sentinel-2 collections. In addition to Earth Search, a summary will be given of other major STAC APIs including CMR-STAC, which is a catalog of NASA Earth Science data, and the Planetary Computer, a STAC API for public datasets available on Azure. We will talk about the most important extensions that are used in these STAC APIs and give some tips for best practices in your own catalogs. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/99EUP3/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/99EUP3/feedback/ Grand C Talk 2024-09-10T14:00:00-05:00 14:00 00:30 This presentation illustrates a workflow for visualizing and analyzing Cloud-optimized GeoTIFFs and Cloud-Optimized Point Clouds using TiTiler and Lonboard - dynamic tiling and interactive visualization libraries, allowing 2.5D interactive map exploration in Python Jupyter notebooks. foss4g-na-2024-2566-big-eo-data-visualization-in-browser-notebooks Image Processing Alex MandelRajat ShindeChuck Daniels en With the increase in cloud computing proximate to data we needed a way to do large data visualization in the notebook based browser environments. For this talk, we will focus on a use-case for Above Ground Biomass (AGB) analysis for visualizing LiDAR derived AGB reference maps along with forest trails for a study region in BCI, Panama. This use case combines LiDAR with high resolution raster layers in an interactive visualization inside a web-based coding notebook. The notebook is developed with an aim of end-to-end processing in the cloud for the NASA-ESA Multi-mission Algorithm and Analysis Platform (MAAP) [1]. MAAP is an open-source scalable and efficient platform for large-scale processing of NASA and ESA datasets along with user generated datasets related to biomass estimation. In this context, a lot of MAAP user data products are published in cloud-optimized formats and accessible via MAAP Spatio-Temporal Asset Catalog (STAC) endpoints [2]. From the perspective of biomass analysis, raw LIDAR data and derived products play a key role. However, raw LiDAR data, typically consisting of billions of points in LAS/LAZ files are not efficient for cloud-based processing attributed to large data egress cost. Hence, Cloud-Optimized Point Cloud (COPC), a compressed and efficient representation of lidar data is used for publishing LiDAR data to STAC, making it suitable for large-scale geospatial applications. In this presentation, we explore a detailed explanation of the process of converting COPC data into a GeoDataFrame. This involves extracting relevant information from the COPC file, such as point coordinates, attributes, and metadata. We will demonstrate how to perform this conversion using open-source tools and provide code examples for reproducibility. Subsequently, we will present Lonboard [3] - a Python library that allows for interactive visualization of geospatial data. We will showcase how to use Lonboard to visualize the GeoDataFrame containing COPC data. This will include creating a map, adding markers for point features, and customizing the visualization with interactive features such as zooming, panning, and highlighting. To provide context and geographic reference, we will integrate a base map into our visualization using Titiler [4], a dynamic raster tile service. We will demonstrate how to use Titiler to add a base map layer to our Lonboard visualization, enabling users to explore the COPC data in relation to real-world geographic features. Join this talk if you want to - - Understand a science use-case for accessing big EO data from STAC - Explore best practices for converting LiDAR LAS files to COPCs - Understand visualizing COPCs and rasters in a interactive maps using Lonboard and TiTilers - Integrate line/polygon geometry visualization to the above maps References: 1. MAAP - https://maap-project.github.io/ 2. MAAP STAC - https://stac-browser.maap-project.org/ 3. Titiler - https://developmentseed.org/titiler/ 4. Lonboard - https://developmentseed.org/lonboard/latest/ false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TQXWSM/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TQXWSM/feedback/ Grand C Talk 2024-09-10T15:00:00-05:00 15:00 00:30 The NASA funded Lifelines Data Series aims to improve humanitarian outcomes by bridging the knowledge and accessibility gaps that currently exist between humanitarians and the use of remote sensing, Earth science, and geospatial data. foss4g-na-2024-2678-lifelines-data-series-accessibility-and-interpretability-eo-data-for-humanitarians FOSS4G in Government Nicole Hunt en Launched in October 2023, the NASA funded Lifelines initiative is a community-building effort designed to enhance the use of Earth science, remote sensing, and geospatial technology, data, and methods to improve humanitarian outcomes. Lifelines focuses on facilitating cross-disciplinary collaboration between scientists, humanitarians, funders, policymakers, and other stakeholders to identify needs and overcome roadblocks related to the adoption of Earth science and remote sensing. One of the most pressing needs in this domain is data. While there is a vast amount of openly available remote sensing and geospatial data, its use by humanitarians remains relatively low. Throughout the first year of the Lifelines program, our team repeatedly heard from humanitarian partners and community members that, although they recognize the value of Earth science and remote sensing data for their efforts, adoption is limited. Our discussions with the community revealed five key roadblocks: Humanitarians often don’t know what data is useful for their use case. If they know what is useful, they often don’t know what is available. If they know what is available, they often don’t know how to access it. If they know how to access it, they often don’t know how to process it. If they know how to process and analyze it, they often don’t know how to generate quantifiable and meaningful insights for their use case. The Lifelines Data Series is an effort to address these issues. Leveraging insights from our advisors, data experts, and community, the Data Series assembles collections of data resources, called Data Studio Packages, paired with educational information for specific humanitarian use cases. These Data Studio Packages not only aggregate available resources and data but also provide educational and informational resources on their deployment for particular use cases. The focus of the Data Series is not to rehost existing open datasets, but to help humanitarians navigate the available data and resources with a clearer understanding of what they are looking for and how to use it. Initial use cases for the Data Studio Packages have been prioritized using the Caribou Space Beyond Borders Report. However, Lifelines is community-driven, so the Data Studio Packages will also be responsive to community needs and support other Lifelines Programs, such as the upcoming Humanitarian Simulation. The NASA Lifelines Data Series aims to enable humanitarians to effectively harness the power of Earth science and remote sensing data, ultimately enhancing their ability to respond to global challenges with greater precision and impact. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/9TQBYJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/9TQBYJ/feedback/ Grand C Talk 2024-09-10T15:30:00-05:00 15:30 00:30 eoAPI is a cloud-native framework for EO data management that can be used to quickly deploy cloud infrastructure for earth observation data applications. Come learn how eoAPI can be used for applications like site selection and monitoring. foss4g-na-2024-2539-using-eoapi-to-find-land-for-natural-capital-projects Use Case and Applications Henry Rodman en eoAPI is a modern, cloud-native framework for EO data management. It is a software package set that relies on standards like Spatio Temporal Asset Catalog (STAC) to manage massive EO datasets for analysis and applications. Platforms built with eoAPI now manage over a billion STAC items, making them findable, accessible, interoperable, and reusable (FAIR). eoAPI and its family of software packages provide a great foundation for applications with interactive mapping components, API endpoints, and more. No single tool or workflow fits all use cases, and that's where the power of eoAPI comes in. Developed by Development Seed, eoAPI is a collection of configurable components designed to fit any unique data ecosystem. Whether you're working with raster or vector data, or both simultaneously, eoAPI can adapt to your needs. It can serve as a catalog for discovery or be combined with powerful tools to deliver data directly for analysis. And the best part? It can run on a single computer or be deployed on any cloud provider, giving you the freedom and flexibility to work the way you want. To illustrate how it can be used to compose powerful applications in the cloud, we will walk through how NCX is using eoAPI to provide landowners with insights about their land. NCX is cataloging many data sources in a STAC using pgstac, serving dynamic raster tiles with titiler, serving vector tiles with tipg, and extending the functionality of the components to fit the specific needs of its users. The end product is a data-driven marketplace that matches landowners with project developers. The data pipeline synthesizes useful information from hard-to-access public data sources and brings it to real people who want to know more about their land. This case study will show how eoAPI works and why you should think about crafting your next application using eoAPI and its components! false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JC7VKY/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JC7VKY/feedback/ Grand C Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 Talk about STAC and Earth and Observation Data with others involved. foss4g-na-2024-2953-stac-and-eo-data-birds-of-a-feather Use Case and Applications Alex Mandel en Talk about STAC and Earth and Observation Data with others involved. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/WVLYGL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/WVLYGL/feedback/ Grand F Talk 2024-09-10T10:30:00-05:00 10:30 00:30 The Geographic Update Partnership Software (GUPS) team will share how the Census Bureau is using open source GIS tools to create web-based GIS solutions that are innovative, adaptable, and versatile. foss4g-na-2024-2508-open-source-in-u-s-census-bureau-geographic-update-applications FOSS4G in Government Emily VratarichMaria Panaccione en The Census Bureau is enhancing its Geographic Update Partnership Software (GUPS), an open source software GIS application, to more fully utilize open source and web-based technologies. GUPS enables partners to load, display, and edit geospatial data, as well as output standardized files that the Census Bureau then uses to update the Master Address File/Topologically Integrated Geographic Encoding and Referencing (MAF/TIGER) System. GUPS Web is built on QGIS, OpenLayers, and GeoServer. Building on the successful implementation of functionality such as real time sharing of data with partners and automated spatial analysis principles, GUPS Web is introducing new and innovative editing processes for a more streamlined user experience. In this presentation, representatives from the Census Bureau will showcase the technology used in developing the GUPS Web application, explore how GUPS evolved into a cloud native and license-free web-based GIS application, and provide an interactive demonstration of how GUPS Web uses open source tools for the Census Bureau’s geographic partnership programs. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/3RJBQA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/3RJBQA/feedback/ Grand F Talk 2024-09-10T11:00:00-05:00 11:00 00:30 Software engineers from the NYC Department of City Planning will discuss the FOSS4G they are using to build modern public-facing full stack web applications that deliver on agency priorities and obligations to the public. foss4g-na-2024-2527-building-on-full-stack-foss4g-in-the-public-sector FOSS4G in Government Tyler Matteo en The Application Engineering team within the IT Division of the NYC Department of City Planning builds and maintains a suite of full stack web-based geospatial applications including ZoLa, Population FactFinder, and the Equitable Development Data Explorer. Over the past year, we have done extensive work to identify what OSS we should use to build these applications going forward. This process has included replacing parts of our stack, reaffirming choices that have served us well, and eliminating vendor dependencies where possible. Our applications include everything from relational databases, to APIs, to Javascript UI and GIS frameworks. After much R&D and proofs-of-concept, we are currently building a new product that will empower the public to view and understand capital spending in New York City. Releasing this fall, this new application will be the first to put many of our new technology choices into practice. In this talk, we will show how an internal software engineering team within government can build custom, full stack applications on a FOSS stack that satisfy our agency's business needs and obligations to the public. We will show the OSS libraries and frameworks we used at various layers of the application, with particular focus on those concerned with geospatial functionality. On the back end, we will talk about how we use technology such as GDAL and PostGIS to transform and store open data sets for use by our APIs. On the front end, we will show how frameworks such as Maplibre and Deck.gl allow us to be build robust web interfaces that integrate with general-purpose frameworks like React. In addition to discussing specific FOSS, we will touch on the principles and best practices that guide our choices, talk about lessons learned, and identify areas where we are still learning. A team like ours simply could not exist without the countless FOSS tools and libraries that allow us to build software at scale while avoiding vendor lock-in. Through this talk, we hope to show FOSS maintainers and contributors how we are using their software to meet our agency's needs and inspire others within government to do the same. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/U9PYLH/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/U9PYLH/feedback/ Grand F Talk 2024-09-10T11:30:00-05:00 11:30 00:30 How we integrated several FOSS4G SW and standards to go from raw data to user friendly output foss4g-na-2024-2509-using-foss4g-to-process-and-visualize-metoc-data FOSS4G in Government Per Thyselius en The talk will describe the how we used several FOSS products (OpenLayers, MapServer, ZOO-Project, WMS, WPS) to fulfil the need of making METOC data available to end users. The METOC solution includes a set of WMS services for meteorology and oceanography, as well as an advanced processing interface to the METOC WPS processes. Users can view METOC data, ranging from temperatures to wave heights. We will describe the current solution and learnings when creating it. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JRC3C7/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JRC3C7/feedback/ Grand F Talk 2024-09-10T13:00:00-05:00 13:00 00:30 The negative effects of water hyacinth resulting from sewage leakages into freshwater bodies surpasses water poisoning and ecosystem changes. As such, GIS is used to monitor and evaluate water hyacinth. foss4g-na-2024-2536-harnessing-technologies-in-effective-monitoring-and-evaluation-water-hyacinth Infrastructure, Emergency Management, and Humanitarian Nicola Kitumetsi Chiware en Environmental monitoring is also a repetitive and continued observation measurement and evaluation of the environmental parameters to follow changes overall period of time and to assess compliance efficiency of the activity on environmental issue. With this definition in mind, a case study was done and focused on Masvingo region in Zimbabwe, evaluating water contamination in Shahashe and Mucheke rivers as a result of sewage leakages. Change detection used helped understand the change in water hyacinth. The use of Geographic Information System (GIS) proved effective enough to monitor and evaluate areas where hyacinth is mostly distributed along the river. The obtained results showed that GIS and remote sensing were typically easy to adopt and apply. Satellite data and auxiliary data were employed in this study. 10% cloud coverage Landsat images were downloaded for free from the USGS Earth Explore website at https://earthexplorer.usgs.gov. for an accurate representation of the water hyacinth's riverside expansion from 2002 to 2022. 13-band Landsat images were atmospherically adjusted with QGIS software's semi-automatic categorization function. The process of modifying the satellite images taken for accurate interpretation comprised of a few steps. Radiometric adjustment This is computer-based method for minimizing and/or eliminating atmospheric noise, for example haze, in photographs. Images' clouds cover collected using USGS was reduced to 10% to avoid result distortion. Image Classification The study's observations of the shifting land use and land cover along the river were made using Google Earth. Google Earth allowed zooming in on land features and offered free access to satellite imagery on both present and previous land dynamics. The classes of vegetation, built-up areas, forests, grasslands, barren land, shrubs, and agricultural regions were recognized and delineated from the satellite photos. Change detection Change detection was performed on mosaiced classified images to compare changes between aerial photos of the same geographic area taken at distinct periods; and assess the spread of water hyacinth along the river over two or more years. Normalized Different Vegetation Index (NDVI) NDVI determines the amount of vegetation by measuring the difference between near-infrared (NIR), which plants significantly reflect, and red light, which vegetation substantially absorbs/has low reflectance. NDVI always ranges from -1 to +1. High NDVI values, which indicate an increase in the amount of green vegetation, are produced by healthy vegetation's low red light reflection and high near-infrared reflectance. Non-vegetation characteristics including water, clouds, snow, ice, and bare rock and soil surfaces are indicated by NDVI values that are near 0 and decreasingly negative values false https://talks.staging.osgeo.org/foss4g-na-2024/talk/DEHD7B/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/DEHD7B/feedback/ Grand F Talk 2024-09-10T13:30:00-05:00 13:30 00:30 Can opensource tools enable equitable access to parks for 40M people? Yes! Learn how California’s open Parks data is produced and maintained, using QGIS and PostgreSQL for continual updates, incorporating user input, and incrementally improving quality and release efficiency. foss4g-na-2024-2662-park-equity-for-california-producing-open-data-from-opensource-software Open Data Jayita Bhojwani en Providing equitable access to parks for people in the nation’s most populous state requires open data that is reliable, frequently updated, and constantly improving. GreenInfo Network has built and sustained the nation’s best state-wide protected lands database for this purpose. For the last 20+ years we have updated and managed two open data sets – the California Protected Areas Database (CPAD) and the California Conservation Easement Database (CCED). This data depicts the wide diversity of parks and open spaces in California, ranging from the largest National Forests and Parks to small neighborhood parks, and underpins initiatives for park access equity, conservation analysis, land use planning, and more. The “open” intention also extends to how the updates are sourced and curated – with close and consistent engagement that GreenInfo Network initiates with contributing agencies, data providers, and users alike. The data has been maintained on PostgreSQL and QGIS since early 2015. At its inception it was stored in shapefiles, but this format didn’t support multi-user editing. Then for a period it was remotely hosted and managed on proprietary enterprise GIS software, but the challenges with maintaining relationship integrity between the various tables, in addition to the unwarranted complexity, cost, and staffing needs for this solution, made it untenable. The eventual switch to open-source in 2015 with PostgreSQL/PostGIS as the backend data store, and QGIS for editing the data, proved to be the solution with the most usability, functional support, ease of maintenance, affordability, and thereby longevity. In this presentation we will share the history of this data, how it is successfully built and managed on open-source tools, and the incremental improvements these tools have enabled to data quality and to the efficiency of the release process. We will touch on the workflows that allow for incorporating user input, and highlight some of the applications that have been derived from the robustness and usability of this data. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/DX8MMB/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/DX8MMB/feedback/ Grand F Talk 2024-09-10T14:00:00-05:00 14:00 00:30 Discover Janes journey from a traditional publisher to a data-centric company. Learn how OpenGIS standards and knowledge graphs have revolutionized military intelligence delivery, enhanced data interoperability and enabling customers to derive maximum value from our comprehensive intelligence data. foss4g-na-2024-2647-transforming-janes-military-intelligence-via-opengis-standards-and-knowledge-graphs Data Management and Interoperability Ben Conklin en Janes has long been recognized as a premier provider of defense intelligence, traditionally known for its comprehensive publications. In recent years, Janes has embarked on a transformative journey to become a data-centric organization. This presentation will cover our evolution from a traditional publisher to a leading data company, focusing on the creation of the world’s largest collection of foundational military intelligence as a knowledge graph. Central to this transformation has been our adoption of OpenGIS data formats and standards, which have been pivotal in ensuring data interoperability and maximizing value for our customers. Agenda for the talk: -The Journey from Publisher to Data Company -Historical Context and Motivation for Change -Overview of Janes’ legacy in defense intelligence publication. Drivers behind the shift to a data-centric approach: customer demand, technological advancements, and the need for enhanced decision-making tools. -Creating the World's Largest Military Intelligence Knowledge Graph The process of transforming vast amounts of published data into a structured, interconnected knowledge graph. Challenges encountered in data aggregation, normalization, and integration. The role of advanced data management techniques and technologies in this transformation. -OpenGIS Data Formats and Standards: Key Enablers -Importance of Open Standards -How OpenGIS data formats and standards facilitate interoperability. -The role of open standards in ensuring seamless data integration and exchange across diverse systems. Implementation at Janes -Specific OpenGIS standards adopted by Janes and their application in our data workflows. -Case studies demonstrating successful integration of Janes' data with various customer systems using these standards. The primary projects/standards we leverage are: GeoJson Standard PostGIS Koop Project GeoParquet OpenSearch false https://talks.staging.osgeo.org/foss4g-na-2024/talk/FLSWJR/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/FLSWJR/feedback/ Grand F Talk 2024-09-10T15:00:00-05:00 15:00 00:30 An implementation of a discrete global grid system (DGGS) for accelerating geospatial data analysis is discussed. EASE-DGGS forms the backbone of a suite of RESTful APIs designed for addressing important agricultural and environmental challenges. foss4g-na-2024-2658-ease-dggs-a-scalable-framework-for-spatial-analytics Climate, Environment and Sustainability Jeff Thompson en Advocates for discrete global grid systems (DGGS) posit the technology as overcoming the limitations of traditional geographic information systems (GIS), which can accelerate discovery and information generation. In 2020 we developed EASE-DGGS, a hybrid DGGS based on EASE-GRID v2, to address limitations of DGGS, specifically the issue of integration of remotely sensed imagery and vector data within spatial analysis frameworks. As part of the University of Minnesota's GEMS Informatics initiative, the EASE-DGGS library was released into the open source domain in 2024 under an Apache 2.0 license. In this presentation, we will present the information scaling motivation for DGGS. We will also examine GEMS Exchange - a RESTful application programming interface (REST API) built on top of EASE-DGGS. GEMS Exchange is explicitly designed to accelerate knowledge discovery in the agricultural and environmental sectors. The presentation will also discuss the API portfolio, with particular emphasis on a key new dataset developed by the UMN GEMS team for the conterminous United States: advanced prediction of the USDA’s Cropland Data Layer. Our CDL-prediction engine, and the whole of GEMS Exchange was built using free, and open source packages and libraries.The presentation will conclude by examining the potential for data integration and interoperability provided by GEMS Exchange in the era of machine learning. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JPRF38/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JPRF38/feedback/ Grand F Talk 2024-09-10T15:30:00-05:00 15:30 00:30 This presentation focuses on the use of MapStore WebGIS framework to navigate urban scenarios using its 3D tools. Attendees will be presented with an overview of our work related to 3D data visualizations and a selection of use cases. foss4g-na-2024-2505-navigate-urban-scenarios-with-mapstore-3d-tools Use Case and Applications Stefano Bovio en This presentation focuses on the use of MapStore WebGIS framework to navigate urban scenarios using its 3D tools and capabilities. Latest versions of MapStore include improvements and tools related to the exploration of 3D data such as Map Views, Styling, 3D Measurements, Annotations and more. Support for 3D Tiles and glTF models through the Cesium mapping library has also been greatly enhanced to provide support for more powerful integration. Attendees will be presented with an overview of our work related to 3D data visualizations and a selection of use cases around the following topics: visualization of new projects for urban planning, relations between different levels of a city and descriptions of events inside a city. At the end of the presentation attendees will be able to use the presented workflows to replicate them on different urban scenarios using the 3D tools of the MapStore WebGIS application. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/SGSBGQ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/SGSBGQ/feedback/ Grand F Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 Birds of a feather making infrastructure better. foss4g-na-2024-2954-government-infrastructure-emergency-birds-of-a-feather Infrastructure, Emergency Management, and Humanitarian en Birds of a feather making infrastructure better. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/EG7JFC/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/EG7JFC/feedback/ Grand G Talk 2024-09-10T10:30:00-05:00 10:30 00:30 Geospatial awareness can be brought to LLMs to address humanity’s most pressing challenges by using authoritative and cross-sectoral Spatial Knowledge Graphs that are automatically interoperable by location. We will present a technical approach using open-source software. foss4g-na-2024-2674-bringing-geospatial-awareness-to-llms-using-open-source-software Geo AI/ML Nathan McEachen en Advances in Artificial Intelligence are transforming industries, and we can expect geoinformatics to be no exception. Natural language processing (NLP) interfaces using Large Language Models (LLM) should not only be able to make finding data easier, but also should be able to reveal the semantic relationships between networks of features across domains. This could support cross-sectoral collaboration to address the multiple and interrelated challenges humanity faces (i.e., polycrises), including economic, public health, and climate. Recent research indicates that spatial knowledge graphs (SKGs) can help overcome limitations of LLMs with domain-specific and evolving spatial awareness. However, to address polycrises at scale, SKGs across sectors need to be available from authoritative sources and interoperable by location using machine-to-machine readable interfaces as they change over time. This can be achieved using a Geospatial Knowledge Infrastructure (GKI) to allow SKGs to be integrated on-demand so that LLMs can answer ad-hoc questions. We developed an approach using open-source software for managing dependencies and propagation of change between interlinked spatial knowledge graphs that was initially developed for the health sector but is being used to support national spatial infrastructures and climate disaster resiliency efforts, including the U.S. Army Corps of Engineers and the recent Open Geospatial Consortium (OGC) Climate Disaster and Resiliency Pilot (CDRP). Our presentation will provide a more in-depth and technical look than what was presented at the 129th Open Geospatial Consortium members meeting and will incorporate recent learnings. This will include a metamodel abstraction for making features and their semantic spatial relationships with other features findable, accessible, interoperable, and reusable as a part of a GKI architecture and how they can bring geospatial awareness to LLMs. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/9GPBEV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/9GPBEV/feedback/ Grand G Talk 2024-09-10T11:00:00-05:00 11:00 00:30 At Impact Observatory we use convolutional neural networks (CNNs) to produce global 10m Land Use/Land Cover (LULC) maps, updated annually. We detail using large language models (LLMs) for geospatial applications, emphasizing open standards: STAC, WPS, and OGC API - Processes. foss4g-na-2024-2605-ai-wrangling-in-the-early-21st-century Geo AI/ML Mark Mathis en Impact Observatory was founded 4 years ago to focus on the application of convolutional neural networks (CNNs) to produce Land Use/Land Cover (LULC) maps at unprecedented speed and scale. Using 1 billion hand labeled pixels we trained a computer vision model, which we then used in combination with some old fashioned remote sensing to produce the world’s first global 10m LULC map; since updated annually to produce a time series for the last 7 years (available as open data). Building on this foundation, we can now produce LULC maps (and some related derived data products) on demand for any location and time. Large language models (LLMs), or so-called Generative AI, have captured our collective imagination. Whereas CNNs excel at capturing spatial patterns and hierarchical features (which is ideal for image recognition tasks) LLMs are neural networks good at getting context from text. Further, contrary to CNNs, where we spend the time and effort to actually train our own model, with LLMs we don’t bother with training (leaving this to the big tech companies) and instead attempt to adapt pre-trained models to our domain. In order to do so effectively, it is necessary to tailor one’s speech to elicit desired behavior from the LLM (i.e., prompt engineering). But more than that, LLMs excel at writing code (generically) and producing valid inputs for functions (specifically). The latter case is particularly useful for geospatial applications, where we can create context specific tools that the LLM can then interact with on behalf of the user. This is especially important to prevent the LLM from simply making up answers (which it is all too happy to do). Open standards are particularly important here as these give the LLM rich and stable interfaces with which to interact. STAC, of course, which we have discussed in great detail within the community. Less so, WPS and OGC API - Processes, which we focus on here. In particular, we discuss a LangChain toolkit for interacting with Planetary Computer (and by extension any other STAC catalog) and detail the development of a tool for accessing WPS processes (using GeoServer). Finally we focus on a path forward for general geospatial enablement of LLM models through OGC API - Processes interactions (using pygeoapi as the reference implementation). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/APAE8V/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/APAE8V/feedback/ Grand G Talk 2024-09-10T11:30:00-05:00 11:30 00:30 Explore the cutting-edge optimization of spatial data structures and hybrid search in the Apache Lucene Open Source project, and discover how these advancements are leveraged in Retrieval-Augmented Generation (RAG) for Geospatial Generative AI. foss4g-na-2024-2646-optimized-geospatial-indexing-for-hybrid-search-and-geoai Geo AI/ML Nicholas Knize, PhD en In this talk, we will explore the optimization of spatial data structures for large-scale geospatial search, high-dimensional vector search, and geo-analytics, examining specific implementations within the Apache Lucene Open Source projects. We will begin with an overview of the evolution of essential spatial data structures, such as Quad-trees, KD-trees, and R-Trees, which are crucial for efficiently indexing geospatial data. We will analyze the challenges associated with distributed geospatial search and discuss how optimized algorithms enhance search performance and scalability in distributed environments, referencing ongoing performance benchmarks collected over several years (https://home.apache.org/~mikemccand/geobench.html). Next, we will introduce and discuss the complexities of high-dimensional vector data and efficient indexing techniques using structures like HNSW graphs, FAISS, and X-Trees. These structures are designed to achieve fast and accurate high-dimensional retrieval, as demonstrated in community-driven benchmark results (https://home.apache.org/~mikemccand/lucenebench/VectorSearch). This discussion will also cover spatial and vector columnar formats for geo-analytics and KNN search, addressing performance, storage demands, and trade-offs relevant to various hybrid search use cases. Optimization techniques, such as dimensionality reduction using principal component analysis (PCA) and compressed columnar formats for reducing data demand, will be introduced and presented through Apache Lucene's Geo Columnar Format (https://github.com/apache/lucene/pull/1017) and dimensional reduction analytic implementations. Finally, we will integrate these topics and discuss techniques for incorporating geospatial data and analytics into a hybrid search system, enabling retrieval-augmented generation (RAG) in Generative AI applications. We will define hybrid search and RAG, emphasizing their importance in enhancing the context and relevance of geospatial data in generative AI outputs. The talk will also cover the evolution of these implementations within Apache Lucene and Lucenia projects, pivotal for advancing the hybrid search landscape in the open-source community. We will trace the historical development of geospatial indexing and search capabilities, highlight recent advancements and enhancements in geospatial data structures, indexing techniques, and search algorithms, and preview upcoming features and improvements. This discussion will provide insights into the current state and future trajectory of geospatial data retrieval and analytics. By examining the advancements in geospatial and hybrid search within the open-source communities, this presentation sets the stage for community involvement and collaboration to significantly impact the future of geospatial applications in Generative AI. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TCTHBV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TCTHBV/feedback/ Grand G Talk 2024-09-10T13:30:00-05:00 13:30 00:30 Discover real-world lessons using LLMs for Geocoding, STAC Search, and Geospatial analysis. Learn tips for prompt optimization, converting natural language to data structures, and transforming natural language into SQL queries using Open Source libraries and tools. foss4g-na-2024-2530-applying-large-language-models-llms-to-geospatial-search-and-analysis Geo AI/ML Jason Gilman en Every geospatial project begins with a quest for answers. Large Language Models (LLMs) are revolutionizing how we can directly understand user needs through techniques like natural language to data structure conversion. Over the past year, I have been developing innovative approaches such as Natural Language Geocoding and Natural Language STAC search, which have proven to be game-changers in the field of geospatial analysis. In this talk, I will share insights and practical experiences from my work at Element 84, where we've been pushing the boundaries of what's possible with LLMs in geospatial applications. We'll explore how open vision models can be combined with these techniques to enable searching for natural features in specific areas, providing a powerful tool for environmental monitoring, urban planning, and more. We'll also delve into systems we've built to answer scientific questions from documents and databases using advanced techniques like Retrieval Augmented Generation, LLM Agents, and Natural Language to SQL conversion. These systems showcase the potential of LLMs to transform unstructured natural language inputs into structured, actionable data. This talk is designed for the geospatial community, united by a passion for solving problems with open technologies, tools, and approaches. At Element 84, we believe in the power of open source and are eager to share the techniques and lessons we've learned to help others benefit from our experience. Key topics covered in the talk will include: * Converting Natural Language Queries into Data Structures: Learn how to use LLMs and libraries like Pydantic to transform user queries into structured data formats. * Open Source vs. Closed Source LLMs: A comparison of the benefits and trade-offs between using open-source and closed-source language models. * Writing Effective Prompts for LLMs: Tips and best practices for crafting prompts that yield accurate and relevant results from language models. * Natural Language Geocoding: An exploration of how we use the Nominatim (OpenStreetMap) API to convert natural language descriptions into precise geospatial coordinates. * Natural Language to SQL: Techniques for converting natural language queries into SQL statements to interact with databases seamlessly. * Handling Ambiguity: Strategies for managing and resolving ambiguous user inputs to ensure accurate and meaningful outcomes. * Supporting Conversations: How to use LLMs to facilitate interactive and context-aware conversations with users. * Choosing and Using Language Model Libraries: Insights on selecting and effectively utilizing libraries like LangChain and LlamaIndex for various geospatial applications. By the end of this session, attendees will have a comprehensive understanding of how to leverage LLMs to enhance geospatial search and analysis. You'll gain practical tips and insights that you can apply to your own projects, helping to advance the field of geospatial technology through innovative use of LLMs. Join us to discover how these powerful models can transform the way we approach geospatial problems, making data more accessible, analysis more intuitive, and solutions more effective. Let's push the boundaries of what's possible together, using the power of LLMs and open source technology. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/PK3D87/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/PK3D87/feedback/ Grand G Talk 2024-09-10T14:00:00-05:00 14:00 00:30 This research presents a lean AI/ML approach using open-source resources to optimize geospatial-focused AI training data. It employs iterative human-machine teaming and quantitative analysis to enhance data diversity and label quality, enabling efficient and effective GeoAI. foss4g-na-2024-2672-building-lean-ai-ml-open-approaches-to-optimal-training-data Academia Dave Cook en Successful AI and machine learning depend on high-quality training data, with data diversity and quality significantly impacting model performance. Traditional data labeling methods often lack rigor, leading to the selection of redundant or irrelevant data and resulting in poor model performance. Our research promotes a 'lean AI/ML' approach that leverages open-source tools and introduces an open methodology to quantitatively optimize data diversity and label quantity, thus improving ML model performance. In geospatial applications and other traditional approaches, the amount of data needed for labeling is often subjectively determined, leading to unnecessary resource use. We aim to present ways for organizations to address this issue by using open data, open-source tools, and models to experiment with and apply AI effectively without massive upfront financial investments. Our methodology addresses these challenges using an iterative human-machine approach in Computer Vision. We incorporate model-predicted labels and capture human adjustments for individual object classes to systematically optimize the diversity and quantity of labels needed for detection models. Unlike traditional pre-labeling approaches that prioritize efficiency over quality, our method involves training a pre-labeling model on the initial batch of human-created labels. This enables us to identify the required data diversity and quantity of labels needed to optimize a CV model for specific mission needs. We begin by training several pre-labeling models using different common model architecture approaches based on initial human-generated labels. These models generate preliminary labels for the next set of data in a labeling campaign. Throughout the campaign, we continually retrain these pre-labeling models on each labeling batch. We compare the predictions from the pre-labeling models with human-labeled data in each batch, using any differences to adjust the labeling process for each object class. This approach allows us to identify specific deficiencies in the model early in the labeling campaigns. The analysis helps us choose the next set of data for labeling in sequential batches to improve model performance. As the differences in human adjustments to predicted labels decrease over iterations, we see where additional labeled data will have diminishing returns on model performance. By using different model architectures and comparing their outputs, we understand what data benefits models the most. The methodology relies on strategically involving human labelers to optimize the model. Initially, human labelers are shown pre-labeled predictions, allowing them to easily identify and correct significant model inaccuracies. As the iterative cycles progress and the difference between model predictions and human adjustments diminishes, a portion of scenes are given to human labelers without revealing predictions. This process helps identify potential model bias and highlights areas where humans may no longer be able to adjust accurately due to increasingly accurate pre-labeling models. These scenes enable adjustments to the labeling workflows and require additional human review when significant anomalies between predicted and human-labeled data are identified in later stages. This approach is crucial in preventing incorrect human labels from steering data selection and quantity requirements in later stages. Our method reduces the need for a large number of human labelers, instead relying on a smaller group of highly skilled subject matter experts to guide the optimization of pre-labeling models. They use an iterative approach with each batch of data in a labeling campaign. High-quality human labels are crucial for accurately comparing corrected and predicted objects in each scene. Involving experts rather than a large number of human labelers ensures precise labeling, leveraging their expertise to guide data selection and avoid unnecessary labeling. An aspect of this method, which drives operational efficiencies in data labeling campaigns, depends on the quality of human-generated labels and their impact on guiding data selection. This requires using advanced data labeling tools that offer full transparency and dynamic adjustments of quality control and trust score mechanisms. These tools must allow for dynamic adjustments to involve additional human review based on ontology or data scene complexity to avoid misdirection in the data labeling campaign. Our research introduces a systematic approach to quantitatively optimize data labeling campaigns. This method enhances model performance by reducing the number of labels and eliminating unnecessary labeling that does not significantly improve model performance. Organizations can conduct more efficient and targeted data labeling campaigns and experiment with GeoAI effectively. By prioritizing fewer but higher-quality labels and leveraging expert knowledge, this method ensures that the selected data for labeling campaigns is both necessary and adequate. Attendees of this presentation will learn how to curate data using open data and open models as a foundation for discussing AI applications in open geospatial tools. This approach enables organizations to leverage the power of AI and machine learning without the need for substantial upfront investments, making it accessible to a wider range of users and applications in the geospatial field. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/B38M8X/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/B38M8X/feedback/ Grand G Talk 2024-09-10T15:00:00-05:00 15:00 00:30 Geospatial foundation models have arrived and are getting better. We examine how the vector embeddings they provide can be used for clustering, change detection, and natural language-search, and discuss the challenge of scaling these solutions across time and space. foss4g-na-2024-2510-embed-all-the-things-the-promise-of-geospatial-vector-embeddings Geo AI/ML Adeel Hassan en In this talk, we explore the immense potential of vector embeddings from open-source geospatial foundation models to revolutionize Earth observation. In particular, we show how geospatial vector embeddings enable (i) clustering and similarity search, (ii) a more robust and holistic method of change detection, and (iii) searching huge catalogs of imagery with natural language. We emphasize how these capabilities can be built entirely with open-source solutions; these include (among others): open-source geospatial foundation models such as Clay and SkyCLIP, open-source geospatial machine learning libraries such as Raster Vision, and open-source geospatial databases such as PostGIS. Additionally, we discuss some interesting open problems that need to be solved if we want to scale up such approaches to a global level and opportunities for the open-source community to contribute. Vector embeddings have emerged as one of the most important tools from the deep learning revolution. The remarkable ability of deep neural networks to turn complex data such as images and text into semantically meaningful vectors in a kind of abstract concept-space has unlocked all manner of interesting applications. Simultaneously, the proliferation of pre-trained open-source models (“foundation models”), especially those pre-trained on geospatial data, has made it trivial to compress Earth imagery to vector embeddings. The question now is: what can we do with them? In this talk, we present three potential use cases. For our first use case, we show how, at a basic level, vector embeddings can be used to cluster images into semantically meaningful clusters as well as to find images similar to a given image. For our second use case, we demonstrate a more advanced analysis. We show how instead of detecting change for a location by comparing images from two discrete timestamps, we can instead model its entire history using vector embeddings and detect change and anomalies by measuring how much they deviate from the model. This approach has the additional benefit of being robust to seasonal variations throughout the year. For our third use case, we demonstrate the use of a slightly different kind of geospatial foundation model: a vision-language model. We show how vector embeddings from such a model can be used to search images based on their semantic content. This enables searching using natural language queries such as “houses with swimming pools” over large geographical areas such as entire cities or states. Finally, we discuss some engineering challenges involved in deploying such solutions at scale. These include: choosing the chipping grid, efficiently storing and searching tens of millions to billions of vectors, versioning the embeddings, and more. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TEZ9AU/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TEZ9AU/feedback/ Grand G Talk 2024-09-10T15:30:00-05:00 15:30 00:30 AI/machine learning has exploded in prominence and one of the key concepts used in this field is vectors. This talk will introduce demonstrate them in geospatial work. This discussion will show live demos of the technology throughout the talks. foss4g-na-2024-2495-quick-intro-to-ai-ml-vector-data-for-geospatial-folks Geo AI/ML Steve Pousty en In the last two years, AI machine learning has exploded in prominence. One of the key concepts used in the modeling and storage of AI is vectors. There is no doubt vector data management will be a key concern of most people concerned with the lifecycle of data management. Feeling like you should learn more and how you would use them in your data work? Then have I got a talk for you! We will start by explaining the concept of (embedding) vectors and how they are used in the AI life cycle. From there we will go into putting them into a database. Now that those vectors are in a database we can talk about the use cases where the technology makes sense. As opposed to an RDBMS, vector databases are more tightly focused and optimized for particular use cases. To ground this discussion in something more concrete, we will show live demos of the technology throughout the talks. By the time you leave you will have a strong base to go home and explore more (and impress friends at dinner parties). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/7YAYTZ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/7YAYTZ/feedback/ Grand G Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 Discussion Topic: GeoAI and Machine Learning Participants: Data Scientists, GIS Specialists, AI Researchers Objective: To explore the integration of AI and ML in geospatial analysis and its applications. foss4g-na-2024-2955-geo-ai-ml-birds-of-a-feather Geo AI/ML en Write me a description of a quick discussion about Geo AI and ML Sent by Copilot: Sure! Here’s a brief description of a quick discussion about GeoAI (Geospatial Artificial Intelligence) and ML (Machine Learning): Discussion Topic: GeoAI and Machine Learning Participants: Data Scientists, GIS Specialists, AI Researchers Duration: 15-30 minutes Objective: To explore the integration of AI and ML in geospatial analysis and its applications. Key Points: Introduction to GeoAI: Definition: GeoAI combines geospatial data with AI techniques to analyze and interpret spatial information. Components: Involves AI, ML, and deep learning to process and analyze geospatial data 1. Machine Learning in GeoAI: Role of ML: ML algorithms are used to identify patterns and make predictions based on geospatial data. Applications: Examples include land use classification, predicting natural disasters, and optimizing urban planning 2. Deep Learning in GeoAI: Advanced Techniques: Deep learning, a subset of ML, uses neural networks to analyze complex geospatial data. Use Cases: Includes image recognition for satellite imagery, detecting changes in land cover, and enhancing map accuracy 3. Benefits of GeoAI: Efficiency: Automates the analysis of large datasets, saving time and resources. Accuracy: Improves the precision of geospatial predictions and analyses. Innovation: Enables new insights and solutions in fields like environmental monitoring, agriculture, and disaster management 1. Challenges and Future Directions: Data Quality: Ensuring high-quality, accurate geospatial data. Computational Resources: Managing the high computational demands of AI and ML models. Ethical Considerations: Addressing privacy and ethical concerns in geospatial data usage 2. Conclusion: Summary: GeoAI and ML are transforming geospatial analysis, offering powerful tools for a wide range of applications. Next Steps: Encourage participants to explore GeoAI tools and consider potential projects or collaborations. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/N7J9MP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/N7J9MP/feedback/ Grand H Talk 2024-09-10T10:30:00-05:00 10:30 00:30 Throughout much of its life, GDAL has suffered from "random person in Nebraska" syndrome. The GDAL Sponsorship Program relieves the pressure on the keystone individuals who hold up our community's software ecosystem by resourcing "maintenance" activities independently from consulting. foss4g-na-2024-2467-building-the-gdal-sponsorship-program The Business of Open Source Howard Butler en GDAL is a 25 year old software project that provides backbone implementations of formats, network protocols, and processing techniques for the geospatial community. GDAL development had historically been driven by consulting, with most of its development and maintenance coming in the form of a single individual making a business of managing the project. This worked until it could not, and the GDAL Sponsorship Program (GSP) reduced the project's Nebraska Syndrome by growing additional capable maintainers, paying down decades-long technical debt, and changing the economics of project maintenance activities that everyone needs but for which no individual organization can pay. We will describe how it was formed, how it works, and why it was needed for the project that fills such a critical role in our community's software ecosystem. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/AKNUDS/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/AKNUDS/feedback/ Grand H Talk 2024-09-10T11:00:00-05:00 11:00 00:30 OpenPlains Inc. is an open-source geospatial modeling platform designed to equip communities with tools for a climate-resilient future. This talk highlights the challenges and successes of transitioning OpenPlains from academic research to a corporation. foss4g-na-2024-2533-openplains-inc-a-first-year-retrospective Academia Corey White en During this session, I will share my journey over the past year as a first-time founder. Through this story, I aim to uncover some of the unknowns for aspiring FOSS4G founders and spark a broader conversation about a company's role within its open-source ecosystem. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/YF8DRH/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/YF8DRH/feedback/ Grand H Talk 2024-09-10T11:30:00-05:00 11:30 00:30 Pangeo is an ecosystem of OSS tools like Xarray, Dask, Jupyter, Zarr, and others used in large scale geospatial analysis. This talk tells the history of how these tools came together and where they're going today. foss4g-na-2024-2631-pangeo-history-a-tale-of-large-scale-computational-infrastructure The Business of Open Source Matthew Rocklin en Pangeo is an ecosystem of OSS tools like Xarray, Dask, Jupyter, Zarr, and others used in large scale geospatial analysis. This talk tells the history of how these tools came together and where they're going today. This story is interesting because it blends software, science, and funding/collaboration. Pangeo was both an incredible success (revolutionized large-scale raster computation in geoscience) and a failure (struggled to launch into a fully self-sustaining organization/service, despite momentum). It's a story full of lessons for people looking to make change in geo sciences through software development. An outline might look something like the following: Introduction - What problems do these problems solve - Who uses them - Who builds them - They're pretty successful. How did they get this way and what can we learn? Pre-Pangeo Years - Dask and Xarray started within Anaconda and Climate Corp respectively. Both employers gave some time to focus on integration - Grew in popularity, becoming the standard - Developed distributed computing capabilities, suddenly able to easily process terabytes - Geoscientists started wanting to organize around the projects, first Pangeo meeting established Pangeo Working Group - Three institutions started working together (Columbia University, NCAR, Anaconda) - More joined later (UK Met, UCAR, ECMWF) - Started on HPC, but then did a Cloud demo with Kubernetes - Massive shift to cloud computing - Around this time we also brought on Zarr and started to push it as a cloud alternative to HDF5/NetCDF Cloud Infrastructure Management - Pangeo developers started spending lots of time setting up and maintaining Kubernetes clusters for research groups. - This was great! But also terrible to maintain. - Dev work started to slow down a bit Community Development - Fortunately, at the same time community engagement picked up a bunch - Pangeo today has many working groups, discourse forum, workshops, etc.. Pangeo goes Corporate - Original Pangeo developers now all run companies - Dask -> Coiled for compute - Xarray+Zarr -> Earthmover for storage - Jupyter -> 2I2C for cloud notebook environments - Open source work was great for pieces, but services were hard as an OSS community Lessons Learned - Pay engineers and scientists from the same grants - Easy to build momentum when you're solving great pain - OSS is great for tools, less great for cloud services This may not be the right Track (please move around if so). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/F78ZJU/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/F78ZJU/feedback/ Grand H Talk 2024-09-10T13:00:00-05:00 13:00 00:30 In an era of rapidly evolving geospatial technology, integrating open-source solutions with proprietary platforms is crucial for innovative spatial analysis and application development to meet customer mission needs with an all-source approach. foss4g-na-2024-2517-leveraging-arcgis-investments-alongside-foss4g-open-source-data Use Case and Applications Garrett TateGhermay Araya en Esri holds a significant market share in the GIS software industry, with estimates ranging from 10% to 80%, depending on the source. This dominance is particularly pronounced in the Department of Defense (DoD), Intelligence Community (IC), and large state, local, and other governmental organizations, which have substantial ArcGIS investments and extensive user bases. These enterprise users are already reaping the benefits of Free and Open Source Software for Geospatial (FOSS4G) and open-source data within and beyond the ArcGIS environment. This talk will focus on how geospatial practitioners can play a role in supporting and enhancing these investments by leveraging all software and data systems available to them. We'll explore the reciprocal relationship where many FOSS4G-based products and data platforms integrate with the Esri ArcGIS environment and vis-versa. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/9FXWXD/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/9FXWXD/feedback/ Grand H Talk 2024-09-10T13:30:00-05:00 13:30 00:30 Cesium, an open platform for 3D geospatial, continues to advance open source 3D geospatial products and support the growing FOSS4G ecosystem. This talk discusses the value of Cesium’s latest developments in open source products and community building. foss4g-na-2024-2675-the-road-to-10-million-downloads-building-open-source-community State of Software Danielle Stollak en Cesium empowers developers across industries to maximize the potential of their 3D data through an open and interoperable platform to support data compatibility and community collaboration. This year, CesiumJS, our open source JavaScript library for creating 3D globes, hit 10 million downloads. Building a healthy open source community has taken concerted effort over a decade, and we’ve built a sustainable business model around keeping CesiumJS open source and giving our developers the quality they’ve come to expect. Supporting the growth and development of the FOSS4G community within the 3D space is integral to Cesium’s success and continued roadmap. Cesium engineering team continues to build out CesiumJS to improve its functionality and interoperability for the open source ecosystem. Investments Cesium has made into its open source platform in the last year include Bathymetric Data, a SketchFab Integration and making accessible 3D buildings in Japan. The impact of these investments expands the 3D ecosystem, increases access to data, and keeps our open source platform performant and accessible. Beyond our engineering efforts, Cesium invests directly into the 3D geospatial community through its grants program and developer certification track. On our grants side we have continued to support 3D improvements to QGIS, supported YouthMappers kick off into 3D, 3D tile improvements in ThreeJS, and a WebODM/Cesium integration. We also have 90 Cesium Certified Developers and counting that have gone through our free developer certification program. Providing a means of validation and recognition for their hard work to support the 3D community. The impact of Cesium’s community investments helps lower the barrier to ecosystem entry, props up interoperability in the ecosystem, and champions open standards. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JAW3YJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JAW3YJ/feedback/ Grand H Talk 2024-09-10T14:00:00-05:00 14:00 00:30 Last year, Element 84 launched a geospatial technology radar. Now in its second year, our tech radar has expanded to include community submissions and to track the evolution of the technology we covered in last year’s edition. foss4g-na-2024-2550-geospatial-radar-report-2024-evolution-and-evaluation-of-emerging-trends The Business of Open Source Lauren Frederick en Last year at FOSS4G NA, Element 84 launched a Geospatial Tech Radar (2023 version here: https://element84.com/geospatial-tech-radar-23/) to highlight industry trends, technologies, and solutions, while functioning as a knowledge sharing platform for the geospatial community. This year, we are excited to introduce our second edition of the radar with updated trends and tech. In such a rapidly evolving industry, it makes sense that much of what we covered last year will have changed since our last radar. By tracking these changes and adding new technology to monitor, we hope to share information with the community about what we learned throughout this process. More specifically, this talk will present the value we’re trying to achieve for the community, how we improved the processes used to create the radar from last year’s edition, how topics (blips) are generated and assessed including the incorporation of community submissions, and some key themes we have observed over the past year. By outlining the blips included in this year’s edition, we will be able to track how the industry has shifted from version one to version two. With this added context, we discuss whether the technology that we chose to highlight last year truly made as big of a splash as we anticipated that it would. Through this comparison, we'll present a more comprehensive look at the trends we're seeing and where we envision the industry moving in the next year. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/VLJFWS/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/VLJFWS/feedback/ Grand H Talk 2024-09-10T15:00:00-05:00 15:00 00:30 This presentation highlights the importance of Sentinel-2 and other public remote sensing data for processing PlanetScope imagery, demonstrating the critical role of these datasets in enhancing the quality and reliability of Earth observation products. foss4g-na-2024-2544-importance-of-public-remote-sensing-data-for-companies-like-planet Image Processing Mariana Curdoglo en Satellite images play a critical role in Earth observation because they provide valuable data for applications ranging from environmental monitoring to agricultural management. Dove fleet, operated by Planet Labs PBC, delivers medium-resolution, high-cadence imagery of the entire Earth’s landmass. To deliver PlanetScope imagery to their users, Planet processes the images through a pipeline built on publicly available remote sensing data. This presentation would focus on the importance of publicly available remote sensing to companies like Planet. The spectral bands of SuperDove are intentionally designed to match those of Sentinel-2, allowing Sentinel-2 to serve as a reference for on-orbit calibration through simultaneous, intersecting crossovers. As the relative spectral responses between Sentinel 2 and SuperDove are very similar, they can collect crossover scenes from anywhere in the world to perform the on-orbit calibration and are not just limited to well characterized calibration sites where a spectral band adjustment factor can be calculated. Sentinel 2 data is vital to operational delivery of PlanetScope imagery to users. Sentinel 2 is only one of many datasets that is used in the PlanetScope pipeline. In addition to radiometric calibration, Planet utilizes openly available data as reference data for rectification. The reference data is designed and built to support orthorectification of any type of Planet ortho scene on a global scale. This dataset covers the large majority of the global landmass with 2.5 m high resolution ALOS satellite imagery (Antarctica not covered, Greenland partially), while the continental US is still covered by very high-resolution (VHR) airborne imagery (NAIP) with resolution under 1 m. The vertical component of the reference data is derived from the Digital Elevation model with a post spacing under 30m globally. This dataset includes Copernicus 30 meter DEM, USG NED, Intermap World30 and others. The above lists the basic mechanism in the PlanetScope pipeline to deliver a PlanetScope top of the atmosphere radiance product. Planet provides additional processing level, surface reflectance. PlanetScope surface reflectance product is derived from the standard radiance product and is processed to top-of-atmosphere reflectance and then atmospherically corrected to bottom-of-atmosphere reflectance. This product ensures consistency across localized atmospheric conditions, minimizing uncertainty in spectral response across time and location. When converting an image to surface reflectance, water vapor and ozone inputs are retrieved from MODIS near-real-time (NRT) data for same-day collects.The SuperDove fleet does not have atmospheric information on board, without MODIS data planet would not be able to deliver a surface reflectance product. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NFXEPT/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NFXEPT/feedback/ Grand H Talk 2024-09-10T15:30:00-05:00 15:30 00:30 Companies are familiar with traditional Build vs. Buy decision making, but are much less familiar with how Open Source fits into that discussion. Is it the best of both worlds, the worst, or something else all together...? Let's talk. foss4g-na-2024-2630-build-vs-buy-vs-open-source The Business of Open Source Dan Pilone en As a custom software solution provider, our most common competitor is an organization's desire to build a solution in-house. We offer a license free, open source geospatial processing stack called FilmDrop that is used to maintain tens of petabytes of production commercial and open geospatial data. In our interactions with both customers and potential customers we frequently need to help them navigate their build vs. buy decisions; often finding that they're **aware** of open source but unsure how exactly to evaluate it or incorporate it into their plans. At one extreme, they consider open source to effectively be a "build" decision. There may be fewer lines of code they have to write from scratch but they'll still need developers and for all intents and purposes they'll need to keep up with the open source components just like any other. At the other extreme, customers may consider open source the equivalent of free shrink-wrapped software and can't they simply "Download and use it"? Our experience has been that an open source based solution can provide the benefits of a custom solution with cost reductions typically associated with COTS software. For many customers, an open source based solution provides an ideal balance between business specific flexibility and cost and maintenance. Furthermore, depending on the business needs of an organization, an open-source based solution can provide **the best** route to standards compliance and broad interoperability, bar none. In this talk, we'll discuss: - Some of the benefits of incorporating open source into your solution space - That not all open source is created equally. There are various open source "delivery" models and your business needs and your team may benefit from one model more than another; some models may simply be unworkable for you. (e.g. the Linux Distribution model vs. a library or framework vs. a complete product such as QGIS) - The importance of determining whether standards adoption and interoperability are dimensions of your build vs buy decision and the role open source plays in that. - A few models for incorporating open source into your approach, starting with simple component adoption, through clean architectural layering with open source foundations, all the way to evaluating having an outside firm help with your open source selections, implementation, and maintenance, effectively treating your open source components largely as a COTS buy but with much greater visibility and control. - Cost factors to consider in the decision making process including your role, if any, in supporting ongoing development and maintenance of the open source components, internal knowledge and expertise necessary for solution maintenance, and realistic risk assessment of long term viability and security considerations of your approach. - Open-source anti-patterns that, regardless of your best intent, have been demonstrated to produce less than optimal outcomes including unintentional forking of open source code, intentional forking, hero coders/architects, and misplaced expectations of support or roadmap alignment. Throughout this talk we'll reference our experiences with FilmDrop as a case study along with the components and specifications widely used throughout our industry including STAC, stac-server, and more. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/WJ83U7/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/WJ83U7/feedback/ Grand H Birds of a Feather 2024-09-10T16:00:00-05:00 16:00 00:30 Can we make money and care about humanity at the same time? Yes we can. foss4g-na-2024-2956-business-of-open-source-birds-of-a-feather The Business of Open Source Howard Butler en Can we make money and care about humanity at the same time? Yes we can. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RFEDTT/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RFEDTT/feedback/ Grand A Talk 2024-09-11T10:30:00-05:00 10:30 00:30 The W3C Maps for HTML Community Group aims to establish a standard map HTML element, supported and rendered by browsers. It supports full-screen, tiled, and vector maps. Dive into the specification and its integration into GeoServer. foss4g-na-2024-2555-mapml-maps-in-html-with-geoserver-support State of Software Andrea AimePeter Rushforth en The W3C Maps for HTML Community Group is working to define a new map HTML element that would be used to define map contents in a web page and would be directly supported and rendered by web browsers in a standardized way. The specification has support for full screen maps, as well as tiled maps, and vector tiles. The presentation will provide an introduction to the specification, then delve into how the MapML support has been integrated into GeoServer OGC services, with native support for TiledCRSs, as well as tiling and styling. We’ll conclude by discussing the next evolution in the MapML structure and its GeoServer implementation. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/MWYLTN/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/MWYLTN/feedback/ Grand A Talk 2024-09-11T11:00:00-05:00 11:00 00:30 The vector mosaic datastore in GeoServer indexes multiple smaller vector stores into a seamless data source, offering cost savings and speed benefits for large datasets in the cloud. This presentation covers setup, tuning, database migration, and practical applications. foss4g-na-2024-2554-vector-mosaicking-with-geoserver Use Case and Applications Andrea AimeJoseph Miller en The vector mosaic datastore is a new feature in GeoServer that allows indexing many smaller vector stores (e.g., shapefiles, FlatGeoBuf, Geoparquet) and serving them as a single, seamless data source. This has the advantage of cost savings when dealing with very large amounts of data in the cloud, as blob storage bills at a fraction of an equivalent database. It is also faster for specific use cases, e.g, when extracting a single file from a large collection and rendering it fully (e.g. tractor tracks in a precision farming application). Attend this presentation to learn more about vector mosaic setup, tuning, migration from large relations databases, and real world experiences. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/AMZPRM/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/AMZPRM/feedback/ Grand A Talk 2024-09-11T13:00:00-05:00 13:00 00:30 The GRASS GIS community celebrated two milestones last year: its 40th birthday and a sizable grant from the National Science Foundation (NSF). In this talk, we will present how the evolution of GRASS GIS is supported by this funding. foss4g-na-2024-2616-evolution-of-grass-gis State of Software Huidae Cho en The GRASS GIS community was awarded a grant from the NSF Pathways to Enable Open-Source Ecosystem (POSE) program. This program is relatively new and will support the transition of GRASS GIS into a sustainable scientific platform for the creation of new technological solutions to important national and societal problems. We are working together to modernize its build system by migrating from the Autotools to CMake for better cross-platform compilations and an easier integration into the Conda ecosystem, create new standardized datasets, provide workshops to its potential developers and users, and support their activities. These collaborative efforts will bring the 40 years' evolution of GRASS GIS to a wider audience of its potential contributors and users including new generations of software developers, geospatial scientists and researchers, and students for its sustainable growth into the future. As always, we welcome new contributors for development, documentation, and translation! false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ETGHSZ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ETGHSZ/feedback/ Grand A Talk 2024-09-11T13:30:00-05:00 13:30 00:30 For any hydrologic studies, it is a crucial step to delineate watersheds to identify study areas. This talk presents the new Memory-Efficient Watershed Delineation (MESHED) OpenMP parallel GIS algorithm for delineating a large number of watersheds. foss4g-na-2024-2617-an-openmp-algorithm-for-delineating-a-large-number-of-watersheds Image Processing Huidae Cho en The Memory-Efficient Watershed Delineation (MESHED) is a new OpenMP GIS algorithm for delineating a large number of watersheds in parallel. It uses different computing techniques to save memory shared among multiple threads and can solve 50% larger problems than its benchmark algorithm can. It first uses a union data structure to store both input and output data in the same matrix and utilizes statistics about incoming flow cells to reduce computational resources for cell discovery. It then parallelizes delineation of a large number of watersheds in an embarrassingly parallel manner. In this talk, I will present typical challenges in this type of large-scale watershed delineation problems and some details about the new techniques in the algorithm. Finally, I will share benchmark results to highlight the memory efficiency and performance of the new algorithm. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KZCUUA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KZCUUA/feedback/ Grand A Talk 2024-09-11T14:00:00-05:00 14:00 00:30 GeoBlaze is a blazing fast raster analysis engine written in pure JavaScript. You can run computations ranging from basic statistics (min, max, mean, median, and mode) to band arithmetic and histograms in a web browser or on NodeJS. foss4g-na-2024-2583-state-of-geoblaze Image Processing Daniel Dufour en GeoBlaze is a blazing fast raster analysis engine written in pure JavaScript. With geoblaze, you can run computations ranging from basic statistics (min, max, mean, median, and mode) to band arithmetic and histogram generation in either a web browser or a node application. ## presentation This presentation will go over recent updates to GeoBlaze, including improved anti-meridian support and virtual resampling. We will also discuss the roadmap for the next couple years. ## use cases GeoBlaze can be used wherever vectors and rasters meet. You can use it to calculate the hectares of wheat in a country, the change in daily median earth temperature, and identify wildfires in satellite imagery. ## environment Because geoblaze is written in pure JavaScript it can be run in various environments, on an EC2 server, Lambda function, Cloudflare worker, or in the browser. It performs calculations using the CPU, so it is not restricted only to environments where a GPU is available. ## notable dependencies GeoBlaze is built on top of the following open-source projects: dufour-peyton-intersection, georaster, geotiffjs, and calc-image-stats. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/KV98DP/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/KV98DP/feedback/ Grand A Talk 2024-09-11T15:00:00-05:00 15:00 00:30 Tracy will show several art maps she has made, and go through the different software used to make them. She will discuss which formats work for each type of map and how to make your own using freely licensed software. foss4g-na-2024-2475-maps-as-art-using-foss Use Case and Applications Tracy Homer en The maps described in this talk are physical art pieces, not posters or digital maps. The tools used are not necessarily GIS software but also other FOSS for post-processing. Some of the maps in the talk are described here: http://www.tracyhomer.com/ false https://talks.staging.osgeo.org/foss4g-na-2024/talk/DJGR3M/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/DJGR3M/feedback/ Grand A Talk 2024-09-11T15:30:00-05:00 15:30 00:30 Ground sampling on beaches is time-consuming and custom remote sensing flights are expensive. I’ll explore ways to leverage open elevation data (lidar & DEMs) and open source software (R & QGIS) to better understand how plants build dunes. foss4g-na-2024-2538-my-talk-is-just-beach-remote-sensing Academia Michele Tobias en Beaches the world over are under threat from sea level rise. The concept of living shorelines as a way to restore the protective power of beaches and dunes is gaining traction in many coastal areas, but managers need to know more about how plant species work with sand to create dunes. Ground sampling is time-consuming and custom remote sensing flights are expensive. Using a site in California as an example, I’ll explore ways to leverage open elevation data (lidar & DEMs) and open source software (R & QGIS) to better understand how plants build dunes. This workflow is applicable to ecosystems where topography plays an important role in understanding ecological interactions, such as riparian or lakeshore plant communities. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RUMGWL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RUMGWL/feedback/ Grand A Talk 2024-09-11T16:00:00-05:00 16:00 00:30 Sevenson Environmental Services (SES) has integrated FOSS solutions using QGIS and QField, to conduct surficial radiological scans with sub-centimeter GPS quality allowing for real-time data collection, statistical processing, and data visualization. foss4g-na-2024-2506-qgis-and-qfield-uses-for-environmental-remediation Transition to FOSS4G Nathan Smail en QGIS and QField have become essential tools for SES in the processing and visualization of field data, in Environmental Remediation. The customizable nature of the GIS software, allows us the ability to collect, process, and visualize surface gamma scans (SGS) to implement our daily operations at FUSRAP Sites for clients like the U.S. Army Corp. of Engineers (USACE) and the U.S. Environmental Protection Agency (EPA). Available commercial software and methods for conducting SGS’s are proprietary, require data processing to see the survey results, were difficult to customize to fit our purpose, and incurred significant associated costs (if it could be done at all). I was tasked with the problem: find a better system. Previous experience with QGIS, led me to explore other FOSS solutions. Working in collaboration with the GeoNinga’s at the Swiss company OPENGIS.ch, and SES’s Dan Caputo Ph.D., and Terranear PMC’s Don Wadsworth, MS.HP, we have to developed and implemented a sensor framework, which allows QGIS and QField to collect data from external radiological detectors (e.g., Ludlum 2221 w/ NaI 3x3 Probe and Ludlum Model 3001 w/ NaI 3x3), process the data (calculate statistics such as average, minimum, maximum, and standard deviation z-scoring), and visualize the data in real-time to keep our Radiological Protection Technicians (RPTs) safe and provide them live-time data, minimizing the technicians time spent in a contaminated open-excavation. This process, via FOSS, provides Sevenson RPT’s with more information in the field while also eliminating the hours spent processing the scan data to be able to know where the best sampling locations should be. With the QField SGS system, radiological readings can be styled by the sensor value directly (setting a trigger level) or applying statistical z-scoring methods with set standard deviations from the mean of the dataset. The RPT’s can visualize their scans in either style and place physical flags or digital markers at every exceedance or area to sample. This eliminates the need of removing their PPE and leaving the radiological exclusion zone and returning later after post processing the scan data. This saves valuable time, eliminating hours of time bringing the field data tablet back to the offices and puling the proprietary files off the field collection tablet and through another proprietary software to get a csv output. QField collects the data, stores it as a geopackage which can be directly exported as a csv removing the entire processing step from the industry standard method of radiological surface gamma scans. Using QGIS also allows the GIS team the ability to name scanning files, while removing the field technicians having to add them in a radiological zone. The cost of software for Sevenson Environmental Services is now greatly reduced with the integration of FOSS, like QGIS and QField, and are measurably more flexible. These software solutions allow SES to keep client confidence for their Data Quality Objectives (DQO), while also reducing fraudulent data collection due to FOSS. We have also integrated Chain of Custody’s (CoC) into our FOSS solutions to follow samples from collection to disposition while using QR codes within QField. This presentation would fit soundly into both Use Case and Applications or Transition to FOSS4G tracks, showing examples of how sensors can be paired with FOSS on Sevenson Environmental Services’ radiological federal projects. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TRJESC/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TRJESC/feedback/ Grand B Talk 2024-09-11T10:30:00-05:00 10:30 00:30 This talk will present a new approach for making GeoParquet queryable using an Apache Lucene codec and giving the ability to make that data searchable using Apache Lucene and Lucenia's spatial indexing capabilities. foss4g-na-2024-2656-searching-the-spatial-data-lake-bringing-geoparquet-to-apache-lucene Use Case and Applications Wes Richardet en As storage costs continue to rise, the Geospatial community is looking at new ways to integrate with data processing tools and make their data more queryable. This talk will present a new approach that makes GeoParquet queryable using an Apache Lucene codec and gives the ability to make that data searchable using Apache Lucene and Lucenia's spatial indexing capabilities. We will demonstrate how to create a GeoParquet file with spatial indexing enabled and query the file using Apache Lucene. We will also discuss the performance implications of using spatial indexing with GeoParquet and how it can improve the efficiency of querying geospatial data. Many users have consolidated data storage into Parquet, Avro, and Iceberg formats; however, these formats are only sometimes easily queryable. Tools like DuckDB work for small-scale use cases, but a more robust solution is needed for larger datasets. For those already running a search cluster or search solution, extending Apache Lucene to support new formats on disk is a natural progression to interop your data with your existing search solution. Alternatively, users may only adopt new software if it supports their existing storage formats. While gaining familiarity with Apache Lucene may be necessary, it is a core component in numerous search engines used daily. Apache Lucene is a robust and high-performance text search engine library written entirely in Java. Its versatility makes it suitable for various applications requiring comprehensive full-text search capabilities across different platforms. Lucene is extensively used across multiple domains, including search engines, recommendation systems, and data analytics platforms. Serving as the foundational indexing component in popular projects like Apache Solr, Elasticsearch, OpenSearch, and Lucenia, Lucene's integrating advanced features such as spatial indexing and geospatial query capabilities make it particularly well-suited for geospatial applications in the open-source community. Apache Parquet is a columnar storage format widely used in the extensive data ecosystem. It is famous for storing data in data lakes and warehouses. Parquet is efficient for storing and querying large datasets because it stores data in a columnar format, which allows for efficient compression and encoding of data. Parquet is also famous for storing geospatial data because it supports complex data types like arrays and maps, commonly used in geospatial data. GeoParquet is an extension of Parquet that adds support for geospatial data types like points, lines, and polygons. It is a popular choice for storing geospatial data because it allows for efficient storage and querying of geospatial data. One limitation of GeoParquet is that it does not support spatial indexing, making it difficult to query geospatial data efficiently. In this talk, we will present a new approach for making GeoParquet queryable using an Apache Lucene codec, which gives the ability to make that data searchable using Apache Lucene and Lucenia's spatial indexing capabilities. We will demonstrate how to create a GeoParquet file with spatial indexing enabled and query the file using Apache Lucene. We will also discuss the performance implications of using spatial indexing with GeoParquet and how it can improve the efficiency of querying geospatial data. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JZNQHN/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JZNQHN/feedback/ Grand B Talk 2024-09-11T11:00:00-05:00 11:00 00:30 Geoparquet and parquet files in cloud object stores like s3 now house huge lakes of data. Join me for an introductory talk on using Crunchy Bridge for Analytics, a query engine that fuses Postgres and DuckDB for fast, vectorized analytics. foss4g-na-2024-2579-geospatial-analytics-with-geoparquet-and-parquet Data Management and Interoperability Rekha Khandhadia en • What is Geoparquet ? • Difference between Geoparquet and Parquet • What is Vector Analytics? • What Geoparquet got to do with Vector Analytics? • Crunchy Bridge Analytics Overview • Perform analytical queries on Geoparquet, Parquet, CSV, and line delimited JSON files stored in data lakes • GIS Analytics using Crunchy Bridge Analytics • Visualize GIS data from Crunchybridge analytics false https://talks.staging.osgeo.org/foss4g-na-2024/talk/UDVPRA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/UDVPRA/feedback/ Grand B Talk 2024-09-11T11:30:00-05:00 11:30 00:30 I walk you through datasets Overture Map Foundation is building, why you would want to access them, and then some basic ways to start getting them into your workflow. Bonus - you will learn some cloud native geospatial formats and tools. foss4g-na-2024-2535-overture-map-data-what-why-how Open Data Steve PoustyJennings Anderson en Geospatial has now reached a stage where we have large and small companies creating overlapping (and even duplicate) large spatial datasets. Overture Map Foundation’s "is dedicated to the development of reliable, easy-to-use, and interoperable open map data that will power current and next-generation map products. We build this data through a collaborative process that combines technology, data, and support from a wide range of companies.” This talk will walk you through what datasets OMF are building, why you would want to access it, and then some basic ways to start getting it into your workflow, such as importing to QGIS and PostGIS. As a side bonus, you will learn some basic cloud native geospatial formats and tools, such as geoparquet. Come join and learn about creating a single, coordinate, base map for the world. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/UJXZFE/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/UJXZFE/feedback/ Grand B Talk 2024-09-11T13:00:00-05:00 13:00 00:30 UI/UX requires a coherent vision and style to succeed. However, the openness and flexibility of FLOSS can, notoriously, make that difficult. We look at lessons learned when our GIS team collaborated with a team of UI/UX students. foss4g-na-2024-2628-how-to-make-floss-look-good Use Case and Applications Will Field en The City University of New York (CUNY) Mapping Service creates civic focused web maps and provides geospatial analysis around issues like the US census, legislative redistricting, and housing. Over the last several years our team has transitioned to a FLOSS stack. FLOSS provides flexibility that proprietary solutions cannot match. This flexibility has been an indispensable asset to our web mapping team as we have been able to use the same stack to tackle a wide variety of projects. However, a successful user interface requires a consistent style and a good user experience demands a coherent plan, both of which are inherently difficult to forge given too many options. Thus we found, at least at first, that the open-endedness of FLOSS solutions were a UI/UX hurdle rather than an asset. Last spring, we teamed up with UI/UX students at Pratt Institute to come up with solutions for one of our more complex and data heavy web maps: The Long Island Zoning Atlas. The Long Island Zoning Atlas shows what types of housing are allowed across all of the 1200+ zoning districts on Long Island. The map can be filtered based on various different housing ordinances. Overlays show school districts, police precincts, congressional districts and more and selecting a zone brings up further information on each of these categories. Our collaboration with the class from Pratt led to numerous improvements which will be released with next update of the site. This talk deals with the particular UI/UX challenges we confronted when given the freedom of FLOSS and the larger lessons we learned. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/VUAMSB/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/VUAMSB/feedback/ Grand B Talk 2024-09-11T13:30:00-05:00 13:30 00:30 Walk through a small organizations implementation of a Geopackage and how it worked great until it didn't. foss4g-na-2024-2559-the-curious-case-of-the-geopackage Data Management and Interoperability Randal Hale en This talk is going to go over the good, the bad, and the ugly with a geopackage implementation at a county and what we did to fix the issue. Back in 2022, a county had implemented QGIS and Geopackage to maintain some critical address data. Geopackage is the default data format of QGIS. It worked well until it didn’t. This talk will walk through what worked and what didn’t work with this approach as a cautionary tale of knowing when to jump to a database. We will also work through the final product (as it stands now) and how things are going. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/UZBWVD/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/UZBWVD/feedback/ Grand B Talk 2024-09-11T14:00:00-05:00 14:00 00:30 The construction industry uses GIS data and as 3D modeling becomes more prevalent the need for interoperable 3D formats is even more necessary. foss4g-na-2024-2546-structures-in-3d-opening-up-construction The Business of Open Source Dan "Ducky" Little en GEOSPAN is a 35 year old GIS company that continues to act as a startup. In the latest iteration, we have pivoted into the construction and contracting sphere and discovered a truly important field is lacking in open standards for communicating important information. Come discover the unique challenges of working in a corner of the market with limit tooling and interesting problems. Using OpenLayers as a way to view Oblique images, forcing ThreeJS to be a GIS rendering technology, and see the ways we are moving towards an open specification on 3D topologies for features. Working on similar challenges? Come see how we can help move the field forward together. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/AZRQKY/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/AZRQKY/feedback/ Grand B Talk 2024-09-11T15:00:00-05:00 15:00 00:30 XArray is the default choice for geoscience users in Python. The Dask Integration allows scaling out to datasets in the petabyte range. We will dive into common pitfalls and how Dask is addressing those to allow processing massive datasets. foss4g-na-2024-2625-geoscience-at-massive-scale State of Software Patrick Hoefler en When scaling geoscience workloads to large datasets, many scientists and developers reach for Dask, a library for distributed computing that plugs seamlessly into Xarray and offers an Array API that wraps NumPy. Featuring a distributed environment capable of running your workload on large clusters, Dask promises to make it easy to scale from prototyping on your laptop to analyzing petabyte-scale datasets. Dask has been the de-facto standard for scaling geoscience, but it hasn’t entirely lived up to its promise of operating effortlessly at massive scale. This comes up in a few ways: - Correctly chunking your dataset has a significant impact on Dask’s ability to scale - Workers accidentally run out of memory due to: - Data being loaded too eagerly - Rechunking - Unmanaged memory Over the last few months, Dask has addressed many of those pains and continues to do so through: - Improvements to its scheduling algorithms - A faster and more memory-stable method for rechunking - First-of-its-kind logical optimization layer for a distributed array framework (ongoing) Join us as we dive into real-world geoscience workloads, exploring how Dask empowers scientists and developers to run their analyses at massive scale. Discover the impact of improvements made to Dask, ongoing challenges, and future plans for making it truly effortless to scale from your laptop to the cloud. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NT9RKW/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NT9RKW/feedback/ Grand B Talk 2024-09-11T15:30:00-05:00 15:30 00:30 Explore how Rasdaman facilitates efficient handling of complex, multi-dimensional climate datasets in Alaska and the Arctic. See its integration with geospatial tools that streamline data access and provide new ways of interacting with climate data. foss4g-na-2024-2502-rasdaman-hypercubes-for-climate-data-science Climate, Environment and Sustainability Josh PaulKyle Redilla en Global climate models produce complex multidimensional datasets representing climate variables like temperature and precipitation over time and space, often for multiple emissions scenarios. These “data hypercubes” present significant challenges for integration with geospatial tools and infrastructure due to their size and complexity. Traditional databases struggle with these datasets, making storage, querying, and analysis difficult. Specialized technologies are needed to make this data accessible online for geospatial applications. Rasdaman (short for “raster data manager”) is an open-source, highly scalable database management system designed for handling large-scale multidimensional raster data. Rasdaman supports key geospatial protocols, including the OGC’s WMS, WCS, and WCPS, essential tools for facilitating data queries over multidimensional datasets and visualizing geospatial data in mapping applications to make it accessible to a wider audience. Our presentation will demonstrate how the Scenarios Network for Alaska and Arctic Planning (SNAP) has successfully integrated Rasdaman into our geospatial data infrastructure. Rasdaman’s WCPS capabilities enable our public API to access multi-terabyte datasets and return web-friendly JSON for integration into various applications. WCPS also makes “computational styles” possible, so that WMS queries can return styled processed subsets of the data hypercube. We’ll show how this works for climate indicators derived from the Coupled Model Intercomparison Project Phase 6 (CMIP6) datasets and other higher dimensional climate datasets. This platform allows us to produce web tools that access climate data hypercubes in a performant, scalable manner, and to make this climate data accessible to a broader audience. Our goal is to enhance engagement and understanding of climate science among the general public, policymakers, researchers, and indigenous rights-holders in Alaska and the Arctic. Join us to see how Rasdaman fits into our infrastructure and how it makes managing complex climate data efficient and accessible. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/UCECCL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/UCECCL/feedback/ Grand C Talk 2024-09-11T10:30:00-05:00 10:30 00:30 A case study about how DroneDeploy implemented "Datum Harmonization" with PROJ and GDAL to reconcile RTK, PPK, and survey data in varying datums and epochs. This required using the ITRF tectonic motion model in PROJ to achieve sub-centimeter accuracy. foss4g-na-2024-2577-harmonizing-datums-and-tectonic-epochs-in-drone-data-using-proj Use Case and Applications Dan Mahr en DroneDeploy is a cloud-based reality capture platform that allows processing still images from drones into orthomosaics, elevation models, point clouds, and 3D meshes. When captured with standard GNSS, these outputs have absolute accuracy of a few meters, at best. Using high-accuracy methods such as surveyed ground control points (GCPs), Real-Time Kinematic (RTK), and Post-Processed Kinematic (PPK), a spatial accuracy of 1 centimeter can be achieved. But at this scale, the subtle differences between datums and the millimeter-per-year drifting of the tectonic plates will degrade accuracy if not properly handled. In this talk, I will present a case study for how DroneDeploy leveraged PROJ's kinematic transformations to harmonize GCPs, RTK, and PPK data across different datums and epochs. This effort was termed "Datum Harmonization" since it involves reconciling disparate coordinate systems into cohesive whole. This was done without any special input from users, whose background in construction, mining, agriculture, and energy means they often lack esoteric understanding of surveying and geodesy. Among other things, I will discuss: - Why we decided to transform all data to a standard datum and epoch: ITRF2014@2010. - How we performed a kinematic transformation on RTK and PPK imagery, simulating continental drift backwards in time from image capture date to the standard ITRF2014 datum and 2010 epoch. - Why we retained the exact PROJ transformation pipeline to ensure long-term consistency through PROJ updates. - How we inserted the source epoch inside the PROJ pipeline so that it does not need to be provided in calls to gdalwarp or PyProj transformers. - How we handled representing Web Mercator rasters when the only EPSG code for Web Mercator is in the WGS84 datum, not ITRF2014. All slides and materials from this talk will be uploaded to https://github.com/dmahr1/talks/tree/main/2024_FOSS4GNA false https://talks.staging.osgeo.org/foss4g-na-2024/talk/XPHC9U/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/XPHC9U/feedback/ Grand C Talk 2024-09-11T11:00:00-05:00 11:00 00:30 Vector data cubes are powerful multidimensional data structures for the analysis of data whose geospatial coordinates are described by vector geometries. This talk explains recent developments that enable vector data cubes in Xarray and Zarr. foss4g-na-2024-2685-vector-data-cubes-in-python-with-xarray-and-zarr State of Software Ryan AbernatheyDeepak Cherian en Data cubes, traditionally associated with raster data, have transformed how the EO community thinks about data analysis, supporting use cases such as statistical analysis, assessing changes and trends, and training predictive models. Raster data cubes are fundamentally multidimensional. They typically have two spatial dimensions as well as a time dimension, making them a an ideal fit for the Xarray Python package—most data cube analysis in Python today uses Xarray as the container for the data. Vector data cubes extend the concept of data cubes to vector data; instead of describing spatial locations as pixels within a raster grid, each item in the spatial dimension can be a vector geometry, such as a point or a polygon. This data structure is ideal for analyzing timeseries associated with multiple variables across a harmonized set of geometries, such as country- or county-level statistics. Vector data cubes were originally developed in R, via the “stars” package, and, until recently, Python users have not been able to use them. However, some recent developments have now unlocked vector data cubes in Python. These developments include: - The continued evolution of geopandas and shapely for greater interoperability - The support of pluggable, user-defined indexes in Xarray, making it possible to create a “geometry index” - The Xvec package, which ties these concepts together - The CF-Xarray package, which implements serialization conventions for geometries, allowing vector data cubes to be stored in either NetCDF or Zarr This talk will explain how these developments come together to provide a powerful vector data cube experience for Python users. We will demonstrate how to build, query, and save vector data cubes and illustrate their potential to greatly simplify common workflows around climate data analysis. Finally, we will conclude with a survey of some of the remaining challenges around integrating spatiotemporal raster and vector data in Python. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/FEPKLT/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/FEPKLT/feedback/ Grand C Talk 2024-09-11T13:00:00-05:00 13:00 00:30 Exactextract uses a novel algorithm to provide a fast implementation of raster/vector zonal statistics in C++, Python, and R. This talk will compare exactextract to other implementations, demonstrate its usage, and offer tips for getting the best performance. foss4g-na-2024-2491-speeding-up-raster-vector-zonal-analysis-with-exactextract Use Case and Applications Dan Baston en The exactextract library provides a fast algorithm for calculating the intersection between a geometry and a rectangular grid in C++, Python, and R. This has numerous applications, the most important of which is raster/vector zonal statistics, answering questions such as “what are predominant land uses of each watershed?”, “what is the population-weighted mean temperature of each county?”, or “what fraction of each state’s population is exposed to each category of drought?” The exactextract algorithm follows a geometry as it enters and exits each grid cell, allowing identification of partially-covered grid cells in a single pass. A limited number of point-in-polygon tests can then be used to identify cells inside or outside the polygon, with a flood fill algorithm used to propagate this status to adjacent pixels. The result is that the algorithm is able to compute the fraction of each grid cell that intersects a polygon and do so more quickly than algorithms that only check centers but must use a separate point-in-polygon test for each cell. In addition to the performance benefit, accounting for partially covered grid cells may be important in cases where grid sizes are large or polygons have an irregular shape. The implementation of exactextract allows control over the amount of memory that is used, allowing arbitrarily large rasters to be processed with a fixed amount of memory. Through a series of brief case studies, this talk will show how the library offers simple and high-performing solutions to problems in raster/vector zonal statistics. Factors affecting performance will also be discussed, including raster compression methods and chunk sizes, GDAL block cache configuration, and the spatial distribution of input features. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RLJJN7/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RLJJN7/feedback/ Grand C Talk 2024-09-11T13:30:00-05:00 13:30 00:30 Come find out what the last 10 years have rendered with OpenDroneMap and get a taste of what's to come. foss4g-na-2024-2585-opendronemap-state-of-the-project State of Software Stephen Mather en Aimed at developers and end-users, this presentation will cover the current state-of-the-art of OpenDroneMap, toolkit of easy-to-use free and open source computer vision tools turning 3D photos into 3D geographic data (colorized point clouds, orthophotos, surface models, terrain models, 3D meshes and more), whether the images be sourced from street level photos, building interiors, or from small uncrewed aircraft (drones). In the last 10 years, OpenDroneMap has not only filled this gap in free and open source software, but it's proprietary alternatives are now advertising themselves as proprietary alternatives to OpenDroneMap. Come and see what we have accomplished together these last 10 years, and get a glimpse at what the future looks like. This session description modified and updated from the first session description from FOSS4G PDX 2014. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/VNG7PC/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/VNG7PC/feedback/ Grand C Talk 2024-09-11T14:00:00-05:00 14:00 00:30 Discover a fast, scalable hazard mapping service built with Python, cloud and FOSS4G stack. Explore how cloud-optimized GeoTIFFs, virtual rasters and GDAL stack enable efficient location-based querying of hazard data of the world. foss4g-na-2024-2496-lean-and-scalable-raster-lookup-service-built-using-cogs Use Case and Applications Atma Mani en The field of disaster resilience involves querying and computing on large volumes of meteorological and climatological data. Often this data is multi-dimensional, spatio-temporal and is traditionally stored in large, monolithic and records based formats such as CSV or netCDF. These formats can be slow and inefficient to access, especially for specific locations or time periods, posing a challenge for on-demand access or computation. This talk explores the methodology we built using the FOSS4G stack to process, store and query such voluminous geospatial data for both on-demand and batch processing. The service, called Hazard Map Service utilizes **Python, Kubernetes and cloud-native geospatial stack** to build a data-processing pipeline that converts raw data in multiple formats and resolutions into a standardized raster format for various perils such as flood, wind etc. The raster is stored in a cloud-optimized manner using object storage services on the cloud. The second component of the service exposes a REST API which the clients can call to stream the voluminous hazard data from object storage on-demand. The talk gets into detail on how we engineered this service, including the spatial file indexing system (built on open location codes), raster formats, asynchronous GDAL calls, the various optimization experiments we ran, their outcomes and lessons learned. These insights aim to aid the development of similar fast, lean, and cost-effective raster lookup services using cloud-native geospatial stack. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/B3FELH/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/B3FELH/feedback/ Grand C Talk 2024-09-11T15:00:00-05:00 15:00 00:30 California’s 30x30 initiative relies on the assignment of USGS GAP codes to California’s data on protected lands (CPAD & CCED). GreenInfo Network built a system of processes using GeoPandas to assign GAP codes and delineate lands for 30x30. foss4g-na-2024-2681-making-california-s-30x30-data-happen-with-geopandas Use Case and Applications Dariya Draganova en In October 2020, California elevated the role of natural and working lands in the fight against climate change and advanced biodiversity conservation as an administration priority, committing to the goal of conserving 30 percent of lands and coastal waters by 2030. Thus California’s 30x30 was born. To track progress toward the 30% target, a key piece of 30x30 in California is the ability to map, enumerate, and report the land considered protected and conserved for biodiversity. California lands protected by both fee and easement are tracked in two respective databases - the California Protected Areas Database (CPAD) and the California Conservation Easement Database (CCED), which are maintained, updated and released biannually by GreenInfo Network. These databases serve as the foundational data for mapping the lands that count toward 30x30 in California. Lands captured in CPAD and CCED are managed by over 1000 different agencies and target many different uses and goals - from recreation-only urban parks to remote wilderness areas with limited human presence to open space lands that allow grazing. For this reason, not every protected land in CPAD and CCED meets the 30x30 requirements for what counts as conserved and protected for biodiversity specifically. To delineate lands that qualify for 30x30 from those that do not, the California Natural Resources Agency (CNRA) chose the USGS GAP code system to rank the level of protection and conservation of protected lands in California. So in addition to maintaining and updating the data in CPAD and CCED, GreenInfo Network’s partnership with CNRA and role in 30x30 now includes collecting GAP code data and assigning those GAP codes to the lands in CPAD and CCED. To obtain GAP codes for federal, state, and locally managed lands in California, GreenInfo Network relies on three different data sources - the PAD-US database, the California Department of Parks and Recreation (CDPR), and local land managing agencies themselves. The PAD-US database and CDPR provide GAP codes for federal and state managed lands respectively, and this data is readily available, easy to obtain, and stays relatively consistent from one year to another. However, when GreenInfo Network took on the 30x30 project there was no easy way to obtain GAP codes for lands managed by the hundreds of different local and regional land managing agencies, which combined manage a significant percentage of California’s conserved and protected lands. Figuring out which of these locally managed lands qualify and count for 30x30 is a major goal. Being able to track changes in the protection and conservation status of these lands is another important goal, since it results in some lands that previously counted toward 30x30 to no longer count, and others that did not count toward 30x30, to count. Our team at GreenInfo Network has spent the last year and a half developing a robust system that utilizes open source tools like GeoPandas to reliably and repeatedly obtain, track, ingest and assign GAP codes to the lands represented in CPAD and CCED. First, we wanted the end-user - the people working at local land managing agencies - to be able to easily submit GAP code data about their lands to us. For this purpose, we created the 30x30 Toolkits, which allow any local and regional agency to download the data we have specific to their lands in CPAD and CCED in either shapefile or tabular format, to review that data, to assign GAP codes to their lands, and then return that data back to us. These Toolkits are created using GeoPandas and Pandas, and can easily be updated on a daily basis in order to reflect the most up-to-date geometry and attributes we have on local lands in CPAD and CCED. The second part of this system is to ingest submitted GAP codes and assign them to their respective lands in CPAD and CCED. Since many different agencies submit GAP data, we utilize Pandas and GeoPandas to create a master GAP data table, which becomes the most authoritative source of GAP data for local lands since it is based on direct input from local agencies. As the last step in this process, GreenInfo Network assigns GAP codes to lands in CPAD and CCED. Again with the aid of GeoPandas and Pandas, GAP codes for federal lands are assigned with data from PAD-US, GAP codes for state lands are assigned with data from CDPR, and lastly, GAP codes for local lands are assigned with the master GAP data table. Once those GAP assignments are made, CPAD and CCED are the most authoritative and foundational datasets for counting all lands that qualify for 30x30. This end product is used by CNRA to create their publicly accessible 30x30 Conserved Areas Layer to track where we stand in the effort to conserve 30% of land by the year 2030. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/MKBBZV/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/MKBBZV/feedback/ Grand C Talk 2024-09-11T15:30:00-05:00 15:30 00:30 Satellite Tasking (i.e., ordering data from the future) remains non-standard and challenging. We’re leading an effort to develop a community standard for tasking and ordering. This presentation covers the current status, future plans, and demonstrates the API. foss4g-na-2024-2564-the-sensor-tasking-api-stapi-specification Data Management and Interoperability Matthew Hanson en In the last decade hundreds of satellites have been launched, and dozens of startup companies have launched taskable earth observation satellites. While this has led to incredible opportunities to leverage multiple sensors and sensor modalities, the massive increase of data has also created challenges in data management, discovery, and usage. The STAC specification was an important step forward in exposing data to users in a standard way, however the process of actually tasking satellites is still very much non-standard. Each data provider exposes a unique API, if at all. Some data aggregators have created a single tasking API that proxies and translates to multiple data provider APIs, but this is still non-standard, and proprietary. Element 84 has been leading an effort to create a community standard API around how users order future data and how providers respond to those requests. Working with government groups, commercial satellite operators, and data integrators, we have hosted working sprints to develop a specification and open-source tooling to make it easier for more users to order and leverage this data. This year we ran our third tasking sprint in Berlin, working on implementations, documentation, and advanced the spec. This talk will cover the current status of the community tasking API specification, future plans, and a demonstration of how to use the API to order data. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/BPBBYA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/BPBBYA/feedback/ Grand C Talk 2024-09-11T16:00:00-05:00 16:00 00:30 DLG has developed the first iteration of a geospatial OSINT visualization and analytics framework for situational awareness of internet activity globally. This presentation will investigate open-source technologies and data utilized to perform workflow orchestration, data management, analytics, and visualization. foss4g-na-2024-2668-leveraging-foss-to-develop-an-osint-visualization-analytics-framework Use Case and Applications Matthew Whitehead en This presentation will focus on the development of an OSINT visualization and analytics framework, including an overview of the tech stack and data sources as well as a deep dive into some of the technologies used. It will start with an overview of the issues working with OSINT data and how this framework intends to solve those problems. While all aspects of the framework will be covered, there will be a more comprehensive look at the data management and backend pieces of the framework. Integrating OSINT data sources can be challenging due to their level interpretability and completeness and we will focus on how we overcame some of these challenges for the Open Observatory of Network Interference (OONI), Open Cell ID, and World Bank Open Data datasets. Extract, Transform, and Load (ETL) of these data sources is accomplished using an orchestration tool called Metaflow and we will briefly cover how an internal trade study led the adoption of this technology. For a deeper dive into how open-source software was used in development of the framework, we will turn to the data management and backend components of the application. Data management falls into two categories: a Postgresql+Postgis database and AWS S3 object storage. The database is used to store data from the ETL process but also to further transform that data into mappable insights derived. Materialized views and pgcron are used to autogenerate these data aggregations and alembic is used for database version control. SQLAlchemy Object-Relational Mappers (ORMs) are used to ensure data validity and maintain reproducibility. S3 is used to store intermediary ETL files and analytics derived from the data stored in the database. We use DuckDB and Hive partitioning to save analytics into parquet files partitioned by date and country. The backend/API was built using the python web framework FastAPI which has some developer friendly features including the automatic documentation feature. Pydantic is leveraged to ensure data validation in the API. The SQLAlchemy ORMs created for the Alembic migrations referenced above are also used by FastAPI to define data models and streamline the development of CRUD operations and functions. FastAPI also provides a web interface to quickly test endpoints to make sure they are functioning as intended. Additionally, we will discuss the use of PG_Tileserv and PG_Featureserv to generate web map tile services (WMTS) for use in the front-end web mapping application including how database roles control the generation of tiles. We will briefly touch on the technologies used for front end web interface, including React and Mapbox, before jumping into a quick demo of the application. Lastly, there will be a discussion on future work that is planned for future iterations of the OSINT visualization and analytics framework. This will include the subject of multitenancy and protecting user uploaded data, AI powered chat bot search functionality, additional data sources and natural language processing, and more analytic capabilities including spatial modeling, dasymetric mapping, network analysis, predictive analysis and more. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NUKMUA/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NUKMUA/feedback/ Grand F Talk 2024-09-11T10:30:00-05:00 10:30 00:30 NASA GIBS and Worldview enable easy browsing of over 1000 free and open Earth science geospatial data products from NASA and its partners. This talk will highlight the usage, open source software, and future direction of GIBS and Worldview. foss4g-na-2024-2592-nasa-gibs-and-worldview-enabling-open-exploration-of-our-world FOSS4G in Government Matthew Graber en Since 2012, NASA’s Global Imagery Browse Services (GIBS) has served billions of image tiles to users around the world, enabling fast and responsive browsing of thousands of Earth science data products to support science, disaster response, and education. Many of these visualized products are available within hours of being acquired as well as for entire satellite missions which can span decades. GIBS imagery has been the backbone of everything from popular NASA websites such as Worldview and Eyes on the Earth to independent open source projects covering a variety of disciplines. Its ability to integrate with GIS applications such as QGIS and ArcGIS have made it popular among GIS professionals. Both Worldview (the open-source web client for viewing GIBS imagery) and OnEarth (the open-source tiled image server of GIBS) have been adapted by others in the community to create their own services as well. In this presentation, we will provide an overview of GIBS and Worldview usage, explore their implementation, highlight some recent developments, and detail our current and future development objectives. First, we will give a brief history of GIBS and Worldview and discuss how they fit in with the rest of NASA’s Earth Science Division and its open data initiatives. We will then highlight how GIBS and Worldview have been used in open source projects, research, and more. Next, we will discuss usage of GIBS and Worldview in more depth, briefly demonstrating their capabilities and how they can be used by the open source community. Following this demonstration, we will give an overview of the architectures of both GIBS and Worldview, highlighting the free and open source OnEarth tiled image server that is developed and maintained by the GIBS team. We will explain why we initially developed OnEarth and its uniqueness over alternative solutions. This includes an explanation of its primary data format, MRF, and why we use it. We will highlight how other projects at both NASA and other institutions have stood up their own instances of the OnEarth server and Worldview. Finally, we will discuss the future of GIBS and Worldview. This section will cover our efforts to develop a dynamic data-to-image pipeline, a prototype data tile service using LERC tiles for client-side rendering, 3D data visualization demos, and prototype AI integrations for detecting the presence of natural hazards (e.g. volcanic eruptions) and quickly locating relevant GIBS/Worldview imagery based on user-written prompts. We look forward to answering questions about the architecture, usage, and direction of GIBS and Worldview. We are interested in hearing feedback from attendees about what new services and features they would find most valuable for their own use cases. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/JHN3A3/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/JHN3A3/feedback/ Grand F Talk 2024-09-11T11:00:00-05:00 11:00 00:30 Presenting Web-based National Weather Service Forecast Guidance Data Displays Using Free and Open Source Software for Geospatial Technology (an update from our 2013 FOSS4G-NA presentation) foss4g-na-2024-2469-web-based-national-weather-service-guidance-data-displays-using-foss4g FOSS4G in Government David Miller en National Weather Service (NWS) field offices working in collaboration with the National Centers for Environmental Prediction (NCEP) feed data into the National Digital Forecast Database (NDFD), a seamless mosaic of digital forecasts. Data from NDFD is available to the public in raw format as well as web-based displays. However, those displays (circa 2002) were built using static images which provide little user-interaction, i.e. no pan/zoom or data probe capabilities. In addition, the images are created for different sectors of the United States as well as the world, each containing hundreds of static images. Requests for customer-specific sectors generated the need for hundreds more static images, often duplicating pieces of existing static images. In order to overcome those limitations, a development team back in 2013 at the NWS Meteorological Development Laboratory (MDL) created updated versions of the web-based NDFD data displays by combining several Open Source software packages such as OpenLayers, MapServer, Postgres/PostGIS, Leaflet, and GDAL. The updated displays dramatically reduced the number of images needed per world region (resulting in a preprocessing time savings) and increased user interactive capabilities with the data as well via a map window on a web page. Over the years with additions and updates to FOSS4G software as well as moving the development and production systems over to the AWS cloud, the team expanded the web displays to include other datasets such as Air Quality Forecast Guidance, part of the National Digital Guidance Database (NDGD, which provides access to computer generated forecasts to NWS forecasters), and also the National Blend of Models (NBM), which is a nationally consistent and skillful suite of calibrated forecast guidance based on a blend of both NWS and non-NWS numerical weather prediction model data and post-processed model guidance. The updated displays for NDFD and Air Quality Forecast Guidance were recently released into operations for the general public at https://digital.weather.gov and https://airquality.weather.gov, respectively (NBM display is currently reserved only for internal NOAA/NWS use). This talk will present those displays with descriptions of data flow and how the MDL team incorporated FOSS4G. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/WLUZUZ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/WLUZUZ/feedback/ Grand F Talk 2024-09-11T11:30:00-05:00 11:30 00:30 Tufts University's MGGG team helps redistrict states, cities, school districts, and more. In 2022 we had to rewrite multiple tools to meet the size and density of New York City's population. foss4g-na-2024-2479-redistricting-new-york-city-with-districtr FOSS4G in Government Nick Doiron en Districtr.org is a tool for state and local government entities to redraw districts and invite public participation. As state redistricting season was winding down, New York City started considering proposals for city council districts. We had been using MapBox vector tiles to rapidly provide population statistics, but at NYC density and zoom levels we could only upload GEOIDs. Among other changes, population calculations got moved to a server with GeoPandas. Looking forward to future maps, we'd like to consider scaling with a more resilient in-memory database, a 'digital twin' on the server, or multiple zoom levels. The talk will cover Districtr's work in general, and this specific engineering challenge. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZLCSPY/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ZLCSPY/feedback/ Grand F Talk 2024-09-11T13:00:00-05:00 13:00 00:30 Mapillary is a platform for street-level imagery hosting over 2 billion geotagged images from around the world. This talk will explore Mapillary's capabilities, how to download map features, who is contributing, how to contribute, and why. foss4g-na-2024-2543-mapillary-an-open-platform-for-street-level-imagery Open Data Edoardo Neerhut en Since Mapillary launched in 2013, over 2 billion images have been contributed from places as far afield as Antarctica and Zimbabwe. Images can be uploaded from any device that creates geotagged images, whether it be the smartphone you have in your pocket or a commercial grade 360° camera. Every image is processed with computer vision to recreate the world in 3D and extract features useful for map making. These capabilities have attracted all sorts of map builders including advocates for pedestrian safety, humanitarian agencies, state and local transportation departments, OpenStreetMap contributors, ridesharing companies and more. This talk will cover. 1. An overview of Mapillary. 2. Who is contributing and some interesting case studies. 3. How to contribute including cameras, upload tools, and best practices. 4. How to download data using Mapillary's web interface and API. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/CSNYWZ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/CSNYWZ/feedback/ Grand F Talk 2024-09-11T13:30:00-05:00 13:30 00:30 Open data from Google Earth, NASA FIRMS, Sentinel Hub, AllTrails, and Peak Visor are a gold mine of information and potential evidence that can be used in human rights advocacy and international criminal investigations to get justice for the people. foss4g-na-2024-2627-how-gis-takes-down-bad-guys-and-preserves-truth Open Data Jenna Dolecek en Although open GIS data has been used for decades, it is currently having its moment within the human rights and international criminal investigation fields. Aerial photography was one of the first applications of GIS in a conflict setting, when used in World War I to gather intelligence on troop movements and artillery placement. In WWII, GIS was used to prove the existence of Nazi extermination camps. These photos were later made public, sparking outrage across the world. Fast forward to the American invasion of Iraq, satellite imagery was used to try and find evidence of weapons of mass destruction. Nearly twenty years ago, Amnesty International historically first used satellite imagery to expose Zimbabwean dictator Mugabe’s large-scale demolitions of housing settlements. Today, satellite imagery, maps, and other open GIS data are used extensively by human rights monitors and war crimes investigators for advocacy and accountability efforts. Geospatial programs like ArcGIS and imagery vendors such as Maxar are accessible to the public, but they come along with a hefty financial barrier, especially for nongovernmental organizations (NGOs) and volunteer projects. However, open sources have toppled this barrier and have significantly increased accessibility. Yet, many individuals are unaware of the vast amount of resources available or have not considered what some may see as ‘unorthodox’ applications of open GIS data. Programs such as Google Earth, NASA Fire Information Resource Management System (FIRMS), and Sentinel Hub revolutionized “citizen” investigation of human rights violations, war crimes, and more. In one volunteer project, we used these tools to document the extensive use of fire to destroy hundreds of Rohingya villages in Rakhine state, Myanmar from 2015-2019. Using before and after imagery, coupled with historical NASA FIRMS fire data, we were able to demonstrate a campaign of concerted destruction which may amount to, or contribute to, genocide of the Rohingya people. United Nations Investigative Mechanisms, NGOs, and courts have used this data to advocate for accountability. It is hoped that in the near future more evidence of this nature will be used by the International Criminal Court to prosecute war crimes and crimes against humanity. It is already being used to an extent and I imagine the prevalence of open data will make their, and other investigations, easier by having the financial barrier removed as well as having other organizations contribute, easing the burden of investigation. In my very first volunteer project, we used Google Earth to discover and document every detention facility in Tibet and other areas with large Tibetan populations, such as Qinghai and Sichuan Provinces in China. When additional information about a detention facility existed online, we used other GIS data for geolocation, or finding the precise location of a facility. Very little information exists on the facilities, largely due to censorship by China, but when photos did exist, verification was needed in order to corroborate information. We had found a Baidu photo from inside a facility, which showed a mountain with a distinct road or trail in the background. The photo did come along with a location, so using that as a starting point, the hiking trail app AllTrails was used to confirm the trail on the mountain and Peak Visor, a database app of mountains, was used to confirm the mountain’s location and profile. I wrote the first guide on how to use outdoor apps AllTrails and Peak Visor for geolocation. In this presentation, I will use the above mentioned tools to demonstrate how open GIS data was used in these projects. Additionally, how it can be used for other human rights and accountability efforts such as mapping human migration, internally displaced peoples (IDP) camps, attacks on civilians and civilian infrastructure, or the use of fire to destroy villages as collective punishment which is illegal under international humanitarian law. International organizations now routinely use remote sensing and other GIS data for human rights related issues such as environmental monitoring, destruction in conflict, or searching for mass graves. National and international courts use GIS data in legal cases as potential evidence of war crimes, crimes against humanity, and genocide. More and more international organizations and non-governmental organizations are heavily relying on open GIS data, and it appears this trend will continue to expand in the coming years, particularly as open source technology makes the work of holding perpetrators to account more accessible. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/ELYYGL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/ELYYGL/feedback/ Grand F Talk 2024-09-11T14:00:00-05:00 14:00 00:30 The manual design of a new electric power line is a time consuming and costly activity that requires massive . Thus the need of platforms model such as open street map as to meaningfully contribute electricity infrastructure using open source platforms foss4g-na-2024-2501-contributing-electricity-infrastructure-on-osm-data Open Data Wallace Tapiwa Gara en According to recent statistics for Zimbabwe, 8,500,000 inhabitants are without electrification. 60% of the total population lack electrification. Furthermore, in the urban area, 20% are without electricity access while an alarming 79% resides in rural areas. The overwhelming electricity deficit identified in the study area has drawn the attention of energy practitioners and policymakers(Samu, Bekun, & Fahrioglu, 2019).This therefore shows the need for new technologies to fill in the gap The previous methods of designing electricity distribution lines, which mainly depended on drawings and work experience, not only lags behind but also affects work efficiency(Jakubiec & Reinhart, 2013). With the advent of the open street map platform which is a space to add missing information on real world features. However whenever electricity lines are constructed there is a pathway which is known as a wayleave which meant give space for the line such that whenever it is constructed, maintained or repaired there aren’t any disturbances with the local community The introduction of 3D GIS has proven to be a sustaining tool in terms of reducing labor and time thus increasing efficiency. OSM and remote sensing are important tools in electrіfіcatіon projects (Sekhar et al., 2008). Data collection is a fundamental tool in network planning for remote areas. These tools will help planners to avoid those areas which are prone to high faults for example water lodged areas. The provision of affordable electricity energy is necessary for development(Mentіs et al., 2015). Almost all of the systems used by the OSM community to date were mainly based on two-dimensional or two and a half dimensional spatial data. In other words one may find it difficult processing and manipulating spatial data greater than 2D in the existing systems, resulting in inaccurate or at least incomplete information. Furthermore, manipulating and representation of real world objects in 2D GIS with are no longer adequate because new applications demand and increasingly deal with more complex hierarchical spatial data than previously supported(Abdul-Rahman & Pilouk, 2007). One of the sіgnіfіcant drivers of socіo-economic development of a country іs the access to electricity which contributes a lot in health, education, agriculture and environmental sustaіnabіlіty(Kemausuor, Obeng, Brew-Hammond, & Duker, 2011). In Zimbabwe, the current approach of designing of electrical power lines is flawed and leads to time consuming and wastage of resources. Since the beginning of 2010s, OSM has developed into an advanced system for preserving and analyzing geographical and thematic data on spatial objects. The need for 3D information is rising quickly. In some circumstances, such as those involving noise prediction models, water flood models, air pollution models, and geological models, 2D analysis has proven to have drawbacks. The requirement for 3D geo-information has also been answered by 3D urban planning, environmental monitoring, telecommunications, public rescue operations, and landscape design, among other fields(Stoter & Zlatanova, 2003). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/8TDPDG/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/8TDPDG/feedback/ Grand F Talk 2024-09-11T15:00:00-05:00 15:00 00:30 See how to use GeoMoose 4, powered by GeoParquet, to create an entire GIS website in minutes! foss4g-na-2024-2545-deploy-a-webgis-with-no-code-and-no-server State of Software Dan "Ducky" Little en GeoMoose 4 makes deploying a WebGIS easier than ever! Configure a small file with references to your data, run a script, and put the results in a web-accessible folder. That's it. Using a mix of GeoParquet and web workers, GeoMoose 4 provides search, identify, and select style functionality all without requiring a single server-side script. All of your data, on the web in minutes, without a single ongoing license cost. The GeoMoose project has worked to be on the leading edge of WebGIS platforms from day one. Version 1.x focused on extending MapServer to provide an accessible open-source solution for GIS sites. 2.x added rich interactive support using AJAX and a set of PHP scripts to make serving data even easier. 3.x focused on allowing standards and protocols from any provider to stitch together rich mapping experiences. With 4.0, the idea of serving data quickly and easily is pushed even further. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/NJSTRK/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/NJSTRK/feedback/ Grand F Talk 2024-09-11T15:30:00-05:00 15:30 00:30 See a web map but can’t download the data? This talk will focus on how to find the data you want from a web mapping using the tools available in the developer console of your web browser foss4g-na-2024-2522-scraping-geospatial-data-from-web-maps Open Data Peter HermanCarina Hoyer en Often maps displayed on the web lack data that are directly downloadable. However, almost all web maps are “scrapable”, creating scraped data that may be processed using open-source tools. This presentation will cover how to leverage a web browser’s developer console to (1) locate and copy markup (HTML/SVG) used to render the map from the Elements tab, (2) discover and utilize undocumented APIs in the Network tab, and (3) provide insight for basic, high level, “best” practices for these techniques. For the first method, the session will cover how to use regular expressions to extract information from maps rendered as SVG or HTML. For the second method, the session will cover how to send requests to undocumented APIs, so participants can retrieve their desired data. The talk will include methods for parsing and reformatting both point and polygon data, with a detailed, step-by-step walkthrough using R and a “no Code” Google Sheets option. Since applicable for many platforms, parsing methods in Python will also be discussed in brief. Finally, the importance of adequately and responsibly attributing data sourced from the web will be emphasized, supplanted by examples of how data scraped from web maps has been used on projects at NORC. Attendees will learn how to enhance their skills at geospatial data extraction, and participants who create maps on the web will be taught how the underlying data they display may be exposed to web scrapers. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/WWULYZ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/WWULYZ/feedback/ Grand F Talk 2024-09-11T16:00:00-05:00 16:00 00:30 Putting data in a bucket, making it public, generated metadata, publishing an API is not enough. Come discuss the next steps in making data truly accessible and usable for analysts, scientists, and all users. foss4g-na-2024-2565-your-api-is-not-enough-delivering-data-the-last-mile Open Data Alex Mandel en This is our story, the story of the open-source and open-data community. We’re trying to get the data into the hands of all the people who need it to solve whatever real-world issue they’re working on—climate change, agriculture, humanitarian missions, biodiversity loss, urban resilience, and more. We’ve made progress over the years with ISO metadata standards, OGC services specifications, Cloud Optimized formats, CSW, and STAC APIs. Plus, lots of Foss4g projects that implement all these solutions. However, there are still some significant roadblocks between data providers and data users who are not software and web developers. The data has gotten too big to search and download by hand or even download at all. If you want to move to the cloud, you must become a DevOps specialist to deploy Pangeo+JupyterHub or Rocker+Rstudio containers to the right place in the cloud near the data. Then you have to interact with data - we’ve got some great libraries (i.e. gdal/ogr, QGIS STAC plugin, pystac-client, rstac, etc) but these only get you the basics of searching and sometimes opening data. What happens when it’s an authenticated data source or when you must cache your cloud-optimized read to make your analysis repeatable? How about support for queryable STAC properties in extensions? You can see we’re at a point where there needs to be more investment in the last-mile clients to make them easier to use. There have been many achievements along this journey, but there are still a few more to go. This talk is about exploring that history, learning lessons, identifying new challenges, and discussing ways forward for the community to enable better access to data for all. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/9998EL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/9998EL/feedback/ Grand G Talk 2024-09-11T11:00:00-05:00 11:00 00:30 Explore the use of SotA FOSS LLMs to automate metadata generation for geospatial imagery. Learn integration techniques for rapid metadata extraction, enhancing analysis with the power of open-source solutions. foss4g-na-2024-2541-image-metadata-generation-with-foss-llms Geo AI/ML David SiamonNicholas Harvey en In this talk we dive into the image inferencing capabilities of FOSS Large Language Models (LLMs), specifically focusing on geospatial satellite imagery. Our objective is to showcase how these advanced models can be smoothly integrated into data pipelines to automate the generation of image metadata. Key Topics Covered: Technical Guide: 1. Image Processing Workflow: A detailed explanation of the workflow used to generate metadata from satellite images, such as the use of bounding boxes and iterative prompts to extract features. 2. Step-by-Step Integration: A practical guide on how to incorporate FOSS LLMs into existing geospatial data pipelines. 3. Customization and Flexibility: A demonstration of how tuning the LLM’s prompts can tailor the metadata extraction to meet specific needs, providing flexibility beyond traditional deep learning techniques. Advantages of FOSS LLMs: 1. Efficiency and Speed: Highlighting how these models can perform complex inferencing tasks quickly. 2. Flexibility in Metadata Extraction: Emphasizing the ease of adapting the model to extract different types of metadata through simple prompt adjustments. 3. Open-Source Benefits: Discussing the advantages of using open-source solutions, including transparency, community support, and the ability to customize and extend the models. Challenges and Solutions: 1. Technical Challenges: Discussion of technical challenges encountered and how they were addressed. 2. Best Practices: Sharing lessons learned and best practices for implementing FOSS LLMs in geospatial workflows. Future Directions: 1. Automation for Real-Time Analysis: Exploring potential extensions such as automating the capture of bounding boxes in real-time drone footage. 2. Advanced Parsing Techniques: Using FOSS tools to parse LLM outputs to extract specific details into structured data formats, enhancing the beginning and end stages of the data pipeline. Impact and Significance: 1. Enhancing Geospatial Analysis: How automating metadata generation with FOSS LLMs can significantly enhance geospatial data analysis. 2. Broader Applications: Potential applications and benefits of this technology in various fields beyond geospatial analysis. Attendees will leave with a thorough understanding of how to integrate FOSS LLMs into their workflows to automate and enhance image metadata generation, as well as a curiosity and interest in further exploring the capabilities of these advanced models. By the end of the session, participants will be equipped with the knowledge and tools to implement FOSS LLMs in their own projects, thereby enhancing their analytic capabilities and efficiency in handling geospatial data. Join us to explore the forefront of automated metadata generation and discover how FOSS LLMs can revolutionize your geospatial workflows with the power of open-source innovation. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/QMGEGQ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/QMGEGQ/feedback/ Grand G Talk 2024-09-11T11:30:00-05:00 11:30 00:30 A discussion of techniques for integrating your application directly with an LLM and how you can work through some of the common pitfalls associated with it. foss4g-na-2024-2570-geospatial-workflows-with-large-language-models Geo AI/ML Joseph Svrcek en When given an overwhelming amount of options, it can be challenging to help a user get to the result they are looking for. Historically we would just add one more filter option, one more search box, or one more tutorial/help feature. In today's environment, you can ask popular chatbots questions like "what type of data" or "how can I use this file", but there is still a manual process of interpreting and implementing the result. In this talk, I'll discuss how we can help an LLM get to the answer we need to feed into the very specific use cases an application. There will be a demo of CartoBot. A python backed web application which takes unstructured user input, like “zoom in”, “fly to paris”, or “color the buildings purple” and leverages ChatGPT to manipulate the map for the user. I discuss some of the techniques used to make this work in a web map. Additionally I'll provide an example of how you could use the same techniques for data selection in an open-source application, Eventkit-Cloud. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/YABGKK/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/YABGKK/feedback/ Grand G Talk 2024-09-11T13:00:00-05:00 13:00 00:30 Tethys Platform is a versatile, feature-rich tool for building web applications for the Earth sciences, using a curated suite of free and open-source software (FOSS), thus enabling effective communication of scientific information to enhance the decision-making processes. foss4g-na-2024-2682-tethys-platform-simplifies-open-source-gis-decision-support-web-applications Use Case and Applications Katherine Moore PowellShawn Crawley en Join us for an insightful exploration of the Tethys Platform, a feature-rich tool for developing and deploying web applications for the Earth sciences. Tethys Platform addresses technical barriers by offering a curated suite of free and open-source software (FOSS) accessible through the Tethys SDK - developers can access powerful tools like OpenLayers, CesiumJS, Bokeh, and Plotly for visualization, and GeoServer, THREDDS, and PostGIS for hosting geospatial and gridded datasets. We will explore the versatility of open-source web GIS and how Tethys Platform enables effective communication of scientific information to enhance the decision-making processes. In collaboration with leading regional organizations worldwide, we will showcase several Tethys portals and web applications that utilize satellite data and geospatial technologies effectively for managing water resources, climate risks, and land use. Further, Tethys promotes interoperability and collaborative decision making while meeting diverse organizational requirements. Our talk aims to provide a holistic understanding of how Tethys Platform uses open-source GIS and web applications to significantly augment decision-making capabilities, stimulate innovation, improve data interoperability, and foster collaboration among GIS professionals, researchers, and policymakers. Additionally, we will discuss the challenges of portability of web applications between different organizations' web servers - government organizations often require hosting and managing web applications on their own servers due to political, branding, and security motivations, rather than relying on third-party websites. Our approach ensures that organizations can leverage advanced environmental analysis tools while maintaining sovereignty over their web applications' deployment and management. Tethys Platform’s many capabilities have garnered significant international interest, evidenced by diverse applications developed by users worldwide. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/3FZK9P/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/3FZK9P/feedback/ Grand G Talk 2024-09-11T13:30:00-05:00 13:30 00:30 This talk will consist of advice for newcomers on building web based mapping tools in R. A brief overview of the relevant R libraries will be followed by specific recommendations for optimizing map load speed and code organization. foss4g-na-2024-2523-fast-organized-interactive-web-maps-with-r-shiny Use Case and Applications Peter HermanCarina Hoyer en This presentation is intended to teach programmers everything they need to know to get started building interactive web maps in R. R Shiny enables programmers to create web maps within the same environment they use for geoprocessing, making it an excellent choice for new programmers to begin with interactive data visualization. Additional, more complex, web mapping alternatives to R Shiny will also be touched upon in the session. First, the presentation will cover the basics of creating a map using the R leaflet library. JavaScript libraries with more advanced visualization capabilities will also be presented: MapBox GL JS (via the MapDeck R library) and D3.js (via the r2d3 library). Examples of web maps built using each library from NORC’s VizStudio will be shown to demonstrate the benefits and drawbacks to each. Step by step programming instructions will be presented for one of the major trouble spots to new R programmers, how to pass spatial data from R to JavaScript. Then, the presentation will cover best practices for building web maps in R Shiny. Organizational strategies for Shiny app code will be discussed, presenting the Golem library, and the ReactR library as alternatives to R Shiny’s native module syntax. Next, we will share techniques for improving map rendering speed, such as simplifying polygons, limiting how much HTML/SVG maps are generating, and determining appropriate levels of reactivity. Finally, we'll provide a brief overview of hosting options for Shiny apps, including AWS, Docker, and Posit solutions like positconnect and shinyapps.io. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/CJDSVW/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/CJDSVW/feedback/ Grand G Talk 2024-09-11T14:00:00-05:00 14:00 00:30 This presentation will highlight the key features of the leafmap Python package for interactive visualization and analysis of geospatial data with minimal coding in a Jupyter environment. foss4g-na-2024-2498-interactive-analysis-and-visualization-of-geospatial-data-with-leafmap State of Software Qiusheng Wu en Geospatial data visualization is essential for understanding and analyzing geographic information. While numerous Python packages exist for visualizing geospatial data, few offer interactive capabilities within the Jupyter environment. This poses a challenge, particularly for novice users with limited coding skills, as loading and displaying geospatial data on an interactive map requires writing extensive code. However, Leafmap, an open-source Python package, addresses this issue by enabling interactive mapping and geospatial analysis with minimal coding in Jupyter notebooks. In this presentation, we will showcase the powerful interactive functionalities of Leafmap for visualizing geospatial data. Attendees will learn how Leafmap simplifies the process of loading and displaying various file formats, including local vector and raster datasets, LiDAR data, Cloud Optimized GeoTIFF (COG), and SpatioTemporal Asset Catalog (STAC). Moreover, we will demonstrate additional interactive features provided by Leafmap, such as the interactive pixel inspector, time slider, and open data search. By the end of this presentation, attendees will have a comprehensive understanding of the capabilities of Leafmap and will be empowered to leverage interactive mapping and geospatial analysis with ease, even with limited coding experience. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RWXUPL/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RWXUPL/feedback/ Grand G Talk 2024-09-11T15:00:00-05:00 15:00 00:30 We’ll explore creating an open-source React-based component library to streamline geospatial web application development at Sparkgeo. We’ll discuss the basic concepts, technical implementation, challenges and benefits to building a component library used across different geospatial projects. foss4g-na-2024-2636-building-a-react-component-library-for-geospatial-web-applications Use Case and Applications Joe Burkinshaw en Most geospatial web applications share similar user interface needs like layer controls, legends, maps and timeline interactions. Instead of building these from scratch every time, we’re working on a library of pre-built, configurable components that can easily be used in a range of projects. We’ll discuss the technical implementation with React’s component-based architecture, and some of the tools used for efficient management and testing. We’re working to make the library map framework agnostic, enabling compatibility with different mapping libraries like Maplibre, OpenLayers and Deck.gl. Building a useful geospatial component library presents some challenges. We’ll cover aspects like establishing development standards, enabling configurability and custom styling to meet project requirements, and managing an open-source project. We believe that engaging the community and encouraging collaboration will help overcome some of these hurdles. While challenging to build, a geospatial component library will support our current and future projects, as well the wider community by offering large time and cost savings, reducing code redundancy, enabling quicker prototyping and facilitating development of robust web map applications. Ultimately, this project aims to provide a valuable resource for efficient and consistent geospatial web development. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/XPZDLB/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/XPZDLB/feedback/ Grand G Talk 2024-09-11T15:30:00-05:00 15:30 00:30 Explore mapping applications in traditional websites using web components as an easy "plug-and-play" solution. Discover the power and benefits of maps as web components, with practical examples of building, testing, and using mapping components in content management systems. foss4g-na-2024-2683-map-as-web-components-how-to-include-map-applications-anywhere Use Case and Applications Yixuan 'Emily' HuOmar Kawach en As map enthusiasts working with geospatial technology, we often see maps at the center stage of a web application, but this isn’t the case for everyone. For most people, maps are solely for navigation, maybe finding nearby restaurants, or occasionally at the end of a web page to see where the place of interest is. There is huge potential for including more GIS in ordinary sites, such as blog sites. With more creative web mapping, GIS developers / mapmakers can express their creativity by introducing interactivity, and readers can get more information out of a web page without being taken out of the website’s ecosystem. The problem is, website creators may not know the intricacies of developing modern web mapping applications. For example, are there any “plug-and-play” solutions that can make inserting a web map as easy as inserting a picture using HTML’s <img></img> tag? Web components are the answer. Web components are custom elements that allow developers to extend HTML and encapsulate complex logic and styling into them. Web components can largely improve the productivity of front-end development, making them very popular among web developers. We, as GIS web developers, can encapsulate complex web mapping libraries into simple web components, allowing them to be “plugged” into a larger website, regardless of the technology the site is based on (e.g., React, Angular, Vue, Wordpress, etc.). Components for mapping applications are gaining popularity There are open-source libraries such as React Leaflet and @planet/maps as well as commercial APIs such as Google’s Maps JavaScript API and Esri’s ArcGIS Maps SDK for JavaScript (web) components. The technical portion of this talk will explore how to wrap popular web mapping libraries into web components and then include them in a website. We will use open-source mapping library for the custom web mapping application. We will share key steps and tips for how to write, test, and maintain web components as well as working with them in open-source and commercial content management systems. Join us for this talk to learn about the power of web components and how to integrate them into your web mapping applications. We’ll also cover insights into the latest trends and technical details of creating and using web components. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/AR8PM8/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/AR8PM8/feedback/ Grand G Talk 2024-09-11T16:00:00-05:00 16:00 00:30 Learn about RESTerville, a cloud-native toolkit for geospatial data management, from its inception to future enhancements. Led by Aaron Laver, this session covers its use in automating data tasks between ArcGIS Online and open source ecosystems. foss4g-na-2024-2477-modernizing-data-automation-introducing-resterville Data Management and Interoperability Aaron M Laver en In this talk, attendees will have the opportunity to gain exclusive insight into RESTerville, an Ohio-born open source software. RESTerville is a cloud-native toolkit that aims to modernize geospatial data management. It can be an organizational game-changer in automating data-related tasks between ArcGIS Online and open source ecosystems, among others. In this session led by Aaron Laver (RESTerville’s lead developer), we’ll cover everything from inception to its current state. Discover the driving force behind its creation and gain valuable insights into the vision that fueled its development. You’ll learn what RESTerville is, what it's for, and when to use it. Stay ahead of the curve as we outline upcoming features and enhancements, keeping you informed about where RESTerville is headed and how it aims to shape the GIS landscape. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/EJRB9X/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/EJRB9X/feedback/ Grand H Talk 2024-09-11T10:30:00-05:00 10:30 00:30 We introduce Raster Tools, an open source, Python package that leverages GDAL bindings and Python’s rich data processing stack to streamline raster processing and GIS work. Raster Tools enables fully parallel processing and automatically scales to available hardware. foss4g-na-2024-2513-introducing-raster-tools State of Software Fredrick Bunt en Python has a rich, general purpose, data processing stack built on tools like Numpy, Xarray, and Dask. With the use of the GDAL bindings like Rasterio, this stack can be leveraged to carry out raster processing and GIS work. It can still be cumbersome and time consuming, however, to develop pipelines that scale from small to extremely large raster datasets. We introduce Raster Tools, an open source, Python package for building scalable and fully parallel raster processing pipelines. Raster Tools takes care of the implementation details so that the user can focus on their model logic. Raster Tools also provides a suite of common raster processing functions including focal, zonal, clipping, and distance operations. Raster Tools uses Dask under the hood for all operations. This allows pipelines built with Raster Tools to automatically scale. Rasters that are too large to fit in memory can easily be processed in parallel on hardware ranging from small laptops to large servers when using Raster Tools. Xarray is used for managing data inside Raster Tools. This allows for easy interoperability with other workflows in Python using Xarray objects. Finally, the suite of provided raster processing functions are accelerated using Numba. The result is functions that run at native compiled speeds, when computation is triggered. This presentation will cover how Raster Tools works, its interoperability with the wider Python ecosystem, and a roadmap for its future. The project is available on GitHub (https://github.com/UM-RMRS/raster_tools). false https://talks.staging.osgeo.org/foss4g-na-2024/talk/RSYZMD/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/RSYZMD/feedback/ Grand H Talk 2024-09-11T11:00:00-05:00 11:00 00:30 Gopher State One Call (GSOC/811) reached out to the Emergency Preparedness Committee of the Minnesota Geospatial Advisory Council about the potential of sharing GIS data in the underground utility community, the result was the Underground Utilities Mapping Project. foss4g-na-2024-2942-fuzionview-sharing-811-call-before-you-dig-data Use Case and Applications Bob Basques en In 2017, representatives of Gopher State One Call (GSOC) reached out to the leadership of Emergency Preparedness Committee of the Minnesota Geospatial Advisory Council (EPC) in hopes of learning what could potentially be done to improve the use of geospatial technology in the underground utility community. From ensuing discussions over the next three years, the Underground Utilities Mapping Project Team (UUMPT) came into existence under the auspices of the EPC in early 2020. Now comprised of over 25 individuals from various sectors of the underground Facility Operator (FO) community, since mid-2021 the UUMPT has been championing development of software called "FuzionView". In October 2022, a FuzionView prototype successfully demonstrated the ability to pull together an on-the-fly, web-mapped view, of all utility infrastructure within a designated dig area. This was a first in the nation achievement. In 2023, GSOC hired Minnesota geospatial research and development nonprofit SharedGeo to develop a production version of FuzionView which will be used across Minnesota and released as Open Source software. Together, these project partners, as well as others who are joining the effort, are working to leverage 50-years of advancements in geospatial technologies that have been previously under-utilized in the underground utility community. Why FuzionView? *** There is no comprehensive or accurate understanding of the infrastructure that is buried in Minnesota or anywhere else in the nation, *** Technology for locating buried infrastructure ("Call Before You Dig") has gone largely unchanged for nearly 50 years, *** Every year, more and more infrastructure is being placed underground, *** Every year, the need to locate this buried infrastructure prior to construction is increasing - it is not uncommon for locate requests in Minnesota to exceed 7,000 in a day, *** In 2021, Minnesota had over 2,200 unintentional hits on underground infrastructure - many of these were on gas lines, *** Without working toward a viable solution for having the mapped location of Minnesota's underground infrastructure, there will be no opportunity in the future to leverage substantial safety and cost saving technologies such as GPS enabled locating equipment and Augmented Reality, and *** Both the U.S. Congress and the Common Ground Alliance have identified the introduction of state-of-the-art geospatial technologies into the buried infrastructure community as a top safety priority. The FuzionView engine will be released as Open Source software at projects completion. The engine has been designed to work with and number of disparate data owners of various online mapping services such as WFS and REST to name a couple and can easily be added to via it's modular implementation framework. All FuzionView services are API driven and use open standards where appropriate, so the integration of FuzionView engine into existing systems requires a very low amount of effort on a developer's part. While this project is currently focused on underground utilities mapping, there are any number of other potential uses for the FuzionView engine for sharing data across other industries. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/MN7JN8/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/MN7JN8/feedback/ Grand H Talk 2024-09-11T11:30:00-05:00 11:30 00:30 When developing pedestrian navigation, safety and efficiency are typically the top priorities. What features should be included on a map to enhance safety for pedestrian navigation? This talk will explore methodologies for generating and ensuring the quality of pedestrian data. foss4g-na-2024-2684-building-map-ready-pedestrian-data Geo AI/ML Yunzhi Lin en When developing pedestrian navigation, safety and efficiency are often the primary considerations. How can we ensure that people are walking on safe and efficient routes? How do we build a map with features that enhance safety for pedestrian navigation? This talk will discuss current mapping approaches to prepare pedestrian data on OpenStreetMap, existing challenges in building this data, and introduce an innovative and streamlined approach to enhance data quality using the MapRoulette challenge framework and community activation. The open source GIS tools we used are • Rapid(https://github.com/facebook/Rapid), • Tasking Manager (https://tasks.mapwith.ai/), • MapRoulette (https://github.com/maproulette) false https://talks.staging.osgeo.org/foss4g-na-2024/talk/UVY8LM/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/UVY8LM/feedback/ Grand H Poster 2024-09-11T13:00:00-05:00 13:00 00:00 The Fridge application quickly connects users to elevation and satellite imagery needed for cryosphere research, using easy to navigate, online tools. Fridge utilizes a number of open source tools such as Geoserver, Airflow, Postgresql and PostGIS. foss4g-na-2024-2526-fridge-providing-access-to-crysophere-data-with-open-source-tools Data Management and Interoperability Rory JohnsonDanny Im en The Federal Researcher Imagery Download and Geospatial Exploration (FRIDGE) System is the Polar Geospatial Center’s (PGC) newly released web application. FRIDGE allows users to navigate Arctic and Antarctic regions, define regions and filters, and immediately retrieve derived elevation data or commercial satellite imagery. FRIDGE is a great resource for publicly available elevation data derived from high resolution commercial satellite imagery. The interface allows users to pinpoint the area they need and retrieve the available data almost instantly from recent or historical releases of ArcticDEM or REMA. Our public DEM data is hosted by Amazon, but organized locally by Geoserver. FRIDGE is also a resource for Federally funded researchers to request access to over 19 Petabytes of historical and modern satellite imagery. PGC maintains an on premise tape library to store and retrieve this massive amount of information. FRIDGE utilizes a number of inter-connected open source frameworks. In the front end we use React and an open source ESRI library to allow users to dynamically navigate and filter our collection of publicly accessible and protected data sets. In the back end we use a tuned Geoserver instance to construct dynamic mosaics, retrieve previews, search the collection and filter results. Geoserver is backed by a Postgresql database utilizing PostGIS for geospatial processing. The front-end communicates with Geoserver utilizing its provided WMS/WFS/WCS services, utilizing an on premise Keycloak instance for authentication and permission handling. The back-end also consists of a Spring based application to facilitate communication between FRIDGE and our Quickbase CRM, allowing our GIS specialists to review, alter, and initiate requests before automated processing starts. In order to process the satellite imagery, collaborate with GIS specialists, and work with PGC's internal HPC cluster, FRIDGE utilizes an Apache Airflow instance. Airflow’s built-in REST APIs allows us to easily integrate it with our hosted Quickbase CRM and back end Spring application. PGC’s GSI specialists can initiate an Airflow job from a customized dashboard and view progress or problems as they happen due to Airflow’s robust reporting infrastructure. Utilizing command line tools on our HPC, Airflow enables FRIDGE to chain together different toolsets to retrieve data from the tape system, automatically orthorectify the data, and move the data to a standardized location for researchers to access. Connecting researchers to the data they need is one of PGC's specialties, by utilizing these powerful open source frameworks they can continue to deliver data efficiently and accurately, while still allowing for specialists to provide guidance and support. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/HVUCZG/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/HVUCZG/feedback/ Grand H Talk 2024-09-11T13:30:00-05:00 13:30 00:30 Learn how the National Oceanic and Atmospheric Administration, together with multiple partners, are working to collect new high-resolution bathymetry to support classification and mapping of benthic habitats within the Great Lakes using open data formats and open source software. foss4g-na-2024-2635-benthic-mapping-efforts-using-open-data-and-open-software Climate, Environment and Sustainability Brandon Krumwiede en Over the last few years, the National Oceanic and Atmospheric Administration (NOAA), together with multiple partners, have been working to collect new coastal and nearshore high-resolution bathymetry, multibeam backscatter, and lidar reflectance to support the classification and mapping of benthic habitats within the Great Lakes, funded through the Great Lakes Restoration Initiative. Bathymetric lidar and multibeam sonar are used to collect these foundational data, combined with underwater video and ancillary data, and are used to derive new and updated classification of the substrate, biotic, and geoform components using the Coastal and Marine Ecological Classification Standard, or CMECS. This presentation will focus on providing an overview of the work completed to date; the importance of open data formats and open source software throughout the project's various workflows; and the potential opportunities for use of these new open data and information to inform benthic ecosystem restoration and protection efforts. Open source software and open data formats are leveraged throughout each phase of the project. The first phase includes gap analysis, mission planning, data acquisition, dataset development, and data QA/QC. This phase leverages QGIS and HydrOffice to evaluate prior existing data coverage and assess new coverage from multiple sources including lidar LAS and LAZ files; multibeam sonar Bathymetric Attributed Grid (BAG) and GeoTIFF files; and other publicly available geospatial datasets to determine which areas have been collected or need to be recollected to meet mission requirements. Additionally, Bathymetry- and Reflectivity-based Estimator of Seafloor Segments (BRESS), GRASS and SAGA are used to perform geomorphometric analysis on the benthic DEM surfaces and used as inputs into the second phase that involves spatial modeling. The second phase includes spatial modeling and analysis to inform ground truthing and underwater video collection deployment efforts. This phase leverages R and RStudio for modeling benthic environment spatial relationships and analysis, while TATOR is used for underwater video annotation. The last phase is data distribution and discovery of all products involved in the project. Resulting data products are provided in multiple formats including LAS/LAZ, Entwine Point Tiles (EPT), Cloud Optimized Point Clouds (COPC), BAG, GeoTIFF/COG for rasters, KML/KMZ, and OpenGeoPackage for vectors to ensure ongoing project collaboration and coordination both internally and externally with partners. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/TZNYFJ/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/TZNYFJ/feedback/ Grand H Talk 2024-09-11T14:00:00-05:00 14:00 00:30 Saildrone manufactures and operates unmanned surface vehicles (USVs) to collect ocean data. For our Maritime Domain Awareness business, we built a cloud-based service to store and filter the ground tracks of other vessels detected by our fleet of USVs. foss4g-na-2024-2519-tracking-detected-vessels-at-sea-from-unmanned-surface-vehicles Use Case and Applications Jeff WangJonathan MasonJian Wu en Saildrones are unmanned surface vehicles deployed for long-duration data collection missions on the ocean. Maritime Domain Awareness ensures the safety and security of waterways, with customers such as the US Navy. Saildrones operating in this area are equipped with sensors, including radar and machine learning-equipped cameras, that track the positions of vessels. Data from these sensors are processed by a mixture of proprietary software and open-source geo libraries and then sent to the cloud in real time. A service in AWS ingests that data into a PostGIS database, where it stores the location of these detected vessels over time. Users can view this data on a map, filter against a geographic region of interest, playback vessel tracks, as well as be notified of newly detected vessels that meet user-selected criteria. Heatmaps are also made using matplotlib for analytics of detections, and we are exploring open-source ways to present this dataset on web maps. Internally, images of the detected vessels are also ingested, not only to provide awareness to our customers, but also to improve machine learning detection models. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/QZ9LX3/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/QZ9LX3/feedback/ Grand H Talk 2024-09-11T15:00:00-05:00 15:00 00:30 NOAA’s Office of Water Prediction leads the development of continental-scale flood inundation mapping (FIM) tools. FIM software is built exclusively using free and open source software, and providing essential services and data for flood preparedness and response efforts. foss4g-na-2024-2665-continental-scale-flood-inundation-mapping-software-for-flood-prediction FOSS4G in Government Robert Hanna en NOAA’s Office of Water Prediction (OWP) leads the development of continental-scale flood inundation mapping (FIM) tools, providing essential services for flood preparedness and response efforts. As flood prediction algorithms become more sophisticated and the volume of output increases, OWP faces challenges in managing the escalating computational demands of flood inundation modeling. The OWP FIM software and technical solutions are built exclusively using free and open source software (FOSS), many of which are geospatial software libraries. Our OWP FIM code solution is a key element of OWP total Flood Inundation Mapping service, available via web pages and web services. We are presenting the FIM software, its usage of FOSS and its impact on the full OWP suite of solutions to produce near real-time flood inundation mapping services at the continental scale covering 3.4 million river miles. Coupled with other OWP forecast products, OWP creates websites and web services that are generally used to create near real-time water prediction data. This data is being used by weather forecasters, city/town emergency management teams, first responders, and the public to increase preparedness for pending flooding events. Our commitment to the scientific community is for FIM software to be fully reproducible, modified or consumed. This commitment includes granting full public access to the OWP FIM code via a GitHub repo. We also encourage you to contribute feedback, code additions, or adjustments to help the product strengthen. Organizations are also welcome to use FIM code as part of their FIM solutions. The OWP FIM solution includes over 50 FOSS libraries and many are geospatial libraries, such as GDAL, Fiona, Pandas, GeoPandas, Rasterio, RichDEM, Shapely, GVAL, TauDEM and PyoGrio to name a few. It is available for viewing at our full GitHub repository at https://github.com/NOAA-OWP/inundation-mapping. You can further view our repo’s “Pipfile” and “Docker” files to view libraries the OWP FIM solution uses. We are happy to present information and examples of how usage of FOSS including OS geospatial software can be used in large scale, complex solutions. Sponsored by NOAA Office of Water Prediction, National Water Center, Tuscaloosa, AL, United States and Lynker Corporation, Boulder, CO, United States false https://talks.staging.osgeo.org/foss4g-na-2024/talk/J88CA9/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/J88CA9/feedback/ Grand H Talk 2024-09-11T15:30:00-05:00 15:30 00:30 Explore how Re:Earth visualizes El Niño-induced flooding in South America in our 30-minute talk. Discover its advanced simulation capabilities that enable effective communication of crucial disaster data, enhancing government response and public preparedness. foss4g-na-2024-2514-re-earth-visualizes-el-nino-floods-in-south-america Use Case and Applications ShogoHirasawa en we will explore a vital application of Re:Earth, the innovative no-code visualization platform, focusing on its role in addressing flood disasters in South America linked to the El Niño phenomenon. Re:Earth enables the visualization of 3D and temporal data, allowing for a dynamic portrayal of disaster evolution over time. Governments often struggle to communicate disaster-related data effectively, despite having access to extensive information. This session highlights how Re:Earth's advanced simulation and visualization technologies can bridge the communication gap between public authorities and citizens. Attendees will learn about the practical benefits of using Re:Earth for disaster preparedness and response, demonstrating the platform's capability to transform complex data into actionable insights that can significantly improve community response strategies. false https://talks.staging.osgeo.org/foss4g-na-2024/talk/GQZGUY/ https://talks.staging.osgeo.org/foss4g-na-2024/talk/GQZGUY/feedback/