BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.osgeo.org//foss4g-2022-academic-track//37JX7T
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-academic-track-CA3TGA@talks.osgeo.org
DTSTART;TZID=CET:20220824T152500
DTEND;TZID=CET:20220824T153000
DESCRIPTION:Soil erosion is a major global land degradation threat. Improvi
 ng knowledge of the probable future rates of soil erosion\, accelerated by
  human activity and climate change\, is one of the most decisive factors w
 hen it comes to making decisions about conservation policies and for earth
 -system modelers seeking to reduce uncertainty on global predictions [1].\
 n\nIn this context\, the use of remote-sensing based methods for soil eros
 ion assessment has been increasing in recent years thanks to the availabil
 ity of free access satellite data\, and it has repeatedly proven to be suc
 cessful [2\, 3]. Accurate information about it is\, however\, usually know
 n only at the local scale and based on limited field campaigns. Its applic
 ation to the Arctic presents a number of challenges\, due to peculiar soil
 s with short growing periods\, winter storms\, wind\, and frequent cloud a
 nd snow cover. However\, the benefits of applying these techniques would b
 e especially valuable in arctic areas\, where ground local information can
  be hard to obtain due to hardly accessible roads and lands.\n\nHere we pr
 opose a hybrid solution\, which uses ground truth samples to calibrate the
  processed remote images over a specific area\, to then automate the analy
 sis for larger\, less accessible areas. This solution is being developed f
 or soil erosion studies of Iceland specifically\, using Sentinel 2 satelli
 te data combined with local assessment data from Iceland’s Soil Conserva
 tion Services department\, Landgræðslan. Their historical data is more e
 xtensive than usual\, since they are the oldest soil erosion department in
  the world.\n\nAvailable data includes parameters of bare ground cover\, w
 hich can be calculated from satellite images alone\, after using informati
 on from observationally correct areas without vegetation for calibration\;
  Icelandic soil profiles\, to be analyzed to find how the profile relates 
 to soil erosion intensity\; as well as the parameters of agriculture use a
 nd arable land data including plant species in cultivated lands.\n\nFor th
 e training phase we employ a dataset composed of 550 cropped georeferenced
  and atmospherically corrected Sentinel 2A images [4]\, combined with a Di
 gital Elevation Model (DEM) of Iceland that allows us to detect slopes whi
 ch can produce landslides or help erosion to occur. The dataset is labelle
 d by six degrees of erosion severity\, using measurement points furnished 
 by Landgræðslan. We split it into 2/3 for model training and 1/3 for mod
 el testing.\n\nThese images are in tiles of 10980x10980 pixels (about 600 
 MB) and cover an area of approximately 100x100 km2. We can crop the images
  down to preferred size. They contain multispectral data\, divided up into
  12 bands of varying wavelengths\, and a resolution from 10 to 20m. We cou
 ld add as well some of the 60m bands if necessary. Different band data are
  combined to create indices which represent or highlight certain features\
 , such as vegetation\, soil crusting\, bare soil\, and red edge indices.\n
 \nElevation data from the Arctic (north of 60°N\, including Iceland) star
 ted to be openly available since 2015 through the ArcticDEM project. The D
 EMs are derived from satellite sub-meter stereo imagery\, particularly fro
 m WorldView 1-3 and GeoEye-1. This information can be used to detect to wh
 at extent plant growth is reduced at higher heights because of longer snow
  cover\, shorter growing period and stronger winds on one side. By using t
 he variation of DEM and building a slope map\, we can see that soil erodes
  more on steep slopes which leads to a higher likelihood of erosion the st
 eeper they are.\n\nThe tools for geometric and topographic correction incl
 ude SNAP (Sentinel application platform)\, Sen2Core\, FLAASH (Fast line-of
 -sight atmospheric analysis of hypercubes)\, DOS (Dark Object Subtraction)
  and ATCOR software. This correction reduces effects due to shadows and su
 rface irregularities and corrects the single-date Sentinel-2 Level-1C Top 
 Of Atmosphere (TOA) products from atmospheric effects in order to deliver 
 a Level-2A Bottom-Of-Atmosphere (BOA) reflectance product.\n\nAfter a prep
 rocessing technique based on dimensionality reduction in order to avoid ad
 ding too much noise to the algorithm\, this labelled data is then used to 
 train a Support Vector Machine (SVM) model for classifying each coordinate
 . We choose the SVM algorithm as a starting point because it is a fast and
  reliable algorithm that performs well for classification problems with hi
 gh-dimensional feature spaces such as ours\, and does not require large tr
 aining sets to achieve high accuracy as other algorithms do (e.g. deep neu
 ral networks). The output of the model is a set of coordinates\, each with
  a numeric classification representing soil erosion severity\, and used fo
 r creating a map of soil erosion severity in a selected area.\n\nThis meth
 odology has been proven to provide good results\, achieving an overall lan
 d cover classification accuracy of 94% [5]\, a performance that can be att
 ributed to the spectral complexity of Sentinel-2 data\, particularly the r
 ed-edge bands which give room for separability of erosion classes. Low sep
 arability is a common limitation to the applicability of classification me
 thods. We address this by using ISODATA and minimum distance methods. Two 
 factors that could affect the accuracy of the delineation of eroded soils 
 using spectral images are the intensity of the soil erosion processes and 
 changes in the spectral characteristics of disturbed soils.\n\nThe researc
 h described here aims at producing a reliable\, widely applicable and cost
 -effective method to classify Icelandic soils into different categories of
  erosion risk\, a proof of concept which\, once engineered\, could be stra
 ightforwardly expanded and applied to other Arctic areas\, such as Greenla
 nd and Canada.
DTSTAMP:20260413T213616Z
LOCATION:Room Hall 3A
SUMMARY:Remote mapping of soil erosion risk in Iceland - Daniel Fernández
URL:https://talks.osgeo.org/foss4g-2022-academic-track/talk/CA3TGA/
END:VEVENT
END:VCALENDAR