BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.staging.osgeo.org//foss4g-2022//talk//SDG9K7
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-2022-SDG9K7@talks.staging.osgeo.org
DTSTART;TZID=CET:20220824T172500
DTEND;TZID=CET:20220824T173000
DESCRIPTION:The use of remote sensing data operating in different observati
 on domains is an undeniable asset for the realization of quality land cove
 r products. \nIndeed\, satellites allow to cover large areas of interest i
 n a regular way with a durable quality. \nSatellite data can be of differe
 nt but often complementary natures\, which makes it possible to broaden th
 e possible fields of application (water management\, snow cover\, crop yie
 ld\, urbanization\, etc.). \nIn addition to these new data\, there are rec
 ent technological developments (or old but now usable due to the evolution
  of computing capacities\, such as the use of neural networks)\, and means
  of service provision and dissemination that allow these applications to b
 e carried out over a longer period of time (long time series that are comp
 uted more rapidly) and in a larger space at different scales\, sometimes s
 imultaneously (stationary\, local\, national\, continental\, global scale)
 .\niota2\, developed by CESBIO and CNES with the support of CS GROUP\, is 
 a response to the growing demand for the creation of an Open Source tool\,
  allowing the production of land cover maps at a national scale that is su
 fficiently generic to be adapted to the different objectives of users. \nI
 n addition\, this project ensures the production of an annual land use map
  of metropolitan France [REF https://doi.org/10.3390/rs9010095]\, with a s
 atisfactory level of quality\, thus proving its operational capacities.\n\
 niota2 integrates several families of supervised algorithms used for the p
 roduction of land use maps. Supervised algorithms (e.g.\,  Random Forests 
 or Support Vector Machine) that process pixels that can be parameterised b
 y the users through a simple configuration file. iota2 also offers the use
 r the option of using a deep learning model.\nIn addition to the pixel app
 roaches\, contextual approaches are also proposed\, with Autocontext [1] a
 nd OBIA (Object Based Image Analysis). Autocontext\, based on RF\, takes i
 nto account the context of a pixel in a window around its position. The OB
 IA approach exploits an input segmentation to classify objects directly.\n
 \nIn addition to the supervised classification approaches\, iota2 is also 
 able to produce indicator maps (biophysical variables) either by supervise
 d regression or by using user-provided processors\, diversifying the possi
 bilities of using iota2.\n\nOne major interest in iota2 is it's ablility t
 o deal with a huge amount a data\, for instance the OSO product (https://t
 heia.cnes.fr/atdistrib/rocket/#/collections/OSO/2327b748-a82c-5933-afb0-08
 7bbfeff4cd) is generated using a stack of all available Sentinel-2 data ov
 er the France without any landscape discontinuity due to the Sentinel-2 gr
 id. Another point of interest is its capability to produce a landcover map
  everywhere a Sentinel-2 data and a groundtruth are available (ie : https:
 //agritrop.cirad.fr/597991/1/Rapport_Intercomparaison_iota2Moringa.pdf). \
 n\n1. Derksen\, D.\, Inglada\, J.\, & Michel\, J. (2020). Geometry aware e
 valuation of handcrafted superpixel-based features and convolutional neura
 l networks for land cover mapping using satellite imagery. Remote Sensing\
 , 12(3)\, 513. http://dx.doi.org/10.3390/rs12030513
DTSTAMP:20260403T230742Z
LOCATION:Modulo 0
SUMMARY:IOTA2: large scale land cover mapping operational chain - Arthur VI
 NCENT
URL:https://talks.staging.osgeo.org/foss4g-2022/talk/SDG9K7/
END:VEVENT
END:VCALENDAR