A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning
Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger un...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://opus.bibliothek.uni-wuerzburg.de/frontdoor/index/index/docId/22299 https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-222998 https://doi.org/10.3390/rs13020197 https://opus.bibliothek.uni-wuerzburg.de/files/22299/remotesensing-13-00197.pdf |
id |
ftunivwuerz:oai:opus.bibliothek.uni-wuerzburg.de:22299 |
---|---|
record_format |
openpolar |
spelling |
ftunivwuerz:oai:opus.bibliothek.uni-wuerzburg.de:22299 2023-09-05T13:13:04+02:00 A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning Dirscherl, Mariel Dietz, Andreas J. Kneisel, Christof Kuenzer, Claudia 2021 application/pdf https://opus.bibliothek.uni-wuerzburg.de/frontdoor/index/index/docId/22299 https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-222998 https://doi.org/10.3390/rs13020197 https://opus.bibliothek.uni-wuerzburg.de/files/22299/remotesensing-13-00197.pdf eng eng https://opus.bibliothek.uni-wuerzburg.de/frontdoor/index/index/docId/22299 urn:nbn:de:bvb:20-opus-222998 https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-222998 https://doi.org/10.3390/rs13020197 https://opus.bibliothek.uni-wuerzburg.de/files/22299/remotesensing-13-00197.pdf https://creativecommons.org/licenses/by/4.0/deed.de info:eu-repo/semantics/openAccess ddc:526 ddc:550 article doc-type:article 2021 ftunivwuerz https://doi.org/10.3390/rs13020197 2023-08-13T22:34:36Z Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km\(^2\)) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a F\(_1\)-score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ... Article in Journal/Newspaper Antarc* Antarctic Antarctica George VI Ice Shelf Greenland Ice Shelf Würzburg University: Online Publication Service Antarctic Austral George VI Ice Shelf ENVELOPE(-67.840,-67.840,-71.692,-71.692) Greenland Pyramid ENVELOPE(157.300,157.300,-81.333,-81.333) Remote Sensing 13 2 197 |
institution |
Open Polar |
collection |
Würzburg University: Online Publication Service |
op_collection_id |
ftunivwuerz |
language |
English |
topic |
ddc:526 ddc:550 |
spellingShingle |
ddc:526 ddc:550 Dirscherl, Mariel Dietz, Andreas J. Kneisel, Christof Kuenzer, Claudia A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
topic_facet |
ddc:526 ddc:550 |
description |
Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km\(^2\)) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a F\(_1\)-score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ... |
format |
Article in Journal/Newspaper |
author |
Dirscherl, Mariel Dietz, Andreas J. Kneisel, Christof Kuenzer, Claudia |
author_facet |
Dirscherl, Mariel Dietz, Andreas J. Kneisel, Christof Kuenzer, Claudia |
author_sort |
Dirscherl, Mariel |
title |
A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
title_short |
A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
title_full |
A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
title_fullStr |
A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
title_full_unstemmed |
A novel method for automated supraglacial lake mapping in Antarctica using Sentinel-1 SAR imagery and deep learning |
title_sort |
novel method for automated supraglacial lake mapping in antarctica using sentinel-1 sar imagery and deep learning |
publishDate |
2021 |
url |
https://opus.bibliothek.uni-wuerzburg.de/frontdoor/index/index/docId/22299 https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-222998 https://doi.org/10.3390/rs13020197 https://opus.bibliothek.uni-wuerzburg.de/files/22299/remotesensing-13-00197.pdf |
long_lat |
ENVELOPE(-67.840,-67.840,-71.692,-71.692) ENVELOPE(157.300,157.300,-81.333,-81.333) |
geographic |
Antarctic Austral George VI Ice Shelf Greenland Pyramid |
geographic_facet |
Antarctic Austral George VI Ice Shelf Greenland Pyramid |
genre |
Antarc* Antarctic Antarctica George VI Ice Shelf Greenland Ice Shelf |
genre_facet |
Antarc* Antarctic Antarctica George VI Ice Shelf Greenland Ice Shelf |
op_relation |
https://opus.bibliothek.uni-wuerzburg.de/frontdoor/index/index/docId/22299 urn:nbn:de:bvb:20-opus-222998 https://nbn-resolving.org/urn:nbn:de:bvb:20-opus-222998 https://doi.org/10.3390/rs13020197 https://opus.bibliothek.uni-wuerzburg.de/files/22299/remotesensing-13-00197.pdf |
op_rights |
https://creativecommons.org/licenses/by/4.0/deed.de info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.3390/rs13020197 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
2 |
container_start_page |
197 |
_version_ |
1776203300840931328 |