BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-europe-2025//speaker//MK
 ULVD
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-foss4g-europe-2025-HMTBTP@talks.staging.osgeo.org
DTSTART;TZID=CET:20250717T163000
DTEND;TZID=CET:20250717T170000
DESCRIPTION:Maps have long been essential tools in both public and private 
 sectors. However\, until recently\, Geographic Information Systems (GIS) a
 nd map creation were largely confined to a small community of highly train
 ed experts. \n\nMainstream adoption has been stifled by several entry barr
 iers: \n\n* the need for specialized domain knowledge in GIS concepts\, da
 ta\, and methodologies\,\n* the technological complexity inherent in data 
 management\, integration\, and processing\,\n* complex user interfaces tha
 t expose too many options (tools and data) &\n* prohibitive software licen
 sing costs\, especially for public institutions in developing countries. \
 n\nThese challenges have often necessitated hiring specialized staff\, the
 reby limiting the proliferation of geospatial technologies among small to 
 medium enterprises and public agencies\, despite the critical role geoinfo
 rmation plays in addressing key 21st-century challenges such as climate ch
 ange adaptation. \n\nRecent advancements in Generative Artificial Intellig
 ence\, especially the emergence of Large Language Models and Agent-Based S
 ystems promise to lower these barriers significantly. In response\, we hav
 e initiated the open-source project NaLaMap (Natural Language Mapping). \n
 \nNaLaMap is designed to democratize access to geospatial information by o
 ffering users the possibility to control key parts of the map creation pro
 cess with natural language commands\, including:\n\n   - data research\, \
 n   - geospatial processing\,\n   - geocoding \n   - layer styling &\n   -
  data integration via OGC compliant protocols (WMS/WFS/WMTS)\n\nThe framew
 ork is built upon widely adopted open-source technologies such as Python (
 Geopandas\, Shapely\, Fiona)\, ReactJS\, LangChain\, Graphagent\, and Leaf
 let. Its core UI-components include a user-friendly chatbot\, an interacti
 ve map interface\, and a data library based on open-data portals. \n\nNaLa
 Maps chatbot automatically geocodes user requests and intelligently search
 es for tools\, datasets\, and unstructured information\, enabling users to
  generate maps with written text commands and evaluate data suitability fo
 r specific data-related questions. This makes it an intuitive tool for you
 r map audience and people who might be overwhelmed by using traditional GI
 S tools. In addition it can also speed up your map creation process and al
 lows you to play arround with cool features such as intelligent (automated
 ) layer styling. \n\nNaLaMap allows adding custom backends\, which enables
  developers to put it on top of their existing geospatial infrastructures.
  Furthermore\, the system offers the possibility to adapt and extend the G
 IS-toolbox offered to the agent as well as the prompts that control its be
 havior and tool usage. \n\nOut talk and open-source software framework is 
 intended for GIS users and developers alike who would try to make their fi
 rst steps with LLMs and GIS without having to create a complete WebGIS fra
 mework from scratch. The purpose of NaLaMap is to increase the reach of ge
 odata products from established teams and projects. In doing so\, it has t
 he potential to empower decision-makers across multiple sectors—from urb
 an planning and environmental monitoring to crisis response. \n\nWith our 
 talk we would like to invite the FOSS4G community to join us in pioneering
  a more accessible\, efficient\, and inclusive future for geospatial intel
 ligence.
DTSTAMP:20260527T184227Z
LOCATION:SA02
SUMMARY:NaLaMap: An open-source framework to use Large Language Models in W
 ebGIS - Johannes Schielein
URL:https://talks.staging.osgeo.org/foss4g-europe-2025/talk/HMTBTP/
END:VEVENT
END:VCALENDAR