Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net
With global warming, supraglacial lakes play an important role in ice sheet stability and climate change. They are not only the main factors affecting mass balance and sea-level rise but also the key units of surface runoff storage and mass loss. To automatically map the spatiotemporal distribution...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14194998 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/14/19/4998/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/14/19/4998/ 2023-08-20T04:06:42+02:00 Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net Di Jiang Xinwu Li Ke Zhang Sebastián Marinsek Wen Hong Yirong Wu agris 2022-10-08 application/pdf https://doi.org/10.3390/rs14194998 EN eng Multidisciplinary Digital Publishing Institute Remote Sensing Image Processing https://dx.doi.org/10.3390/rs14194998 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 14; Issue 19; Pages: 4998 supraglacial lake SAR deep learning Greenland Text 2022 ftmdpi https://doi.org/10.3390/rs14194998 2023-08-01T06:47:21Z With global warming, supraglacial lakes play an important role in ice sheet stability and climate change. They are not only the main factors affecting mass balance and sea-level rise but also the key units of surface runoff storage and mass loss. To automatically map the spatiotemporal distribution of supraglacial lakes in Greenland, this paper proposes an attention-based U-Net model with Sentinel-1 SAR imagery. The extraction results show that compared with the traditional network, this method obtains a higher validation coefficient, with an F1 score of 0.971, and it is spatiotemporally transferable, able to realize the extraction of supraglacial lakes in complex areas without ignoring small lakes. In addition, we conducted a case study in the Jakobshavn region and found that the supraglacial lake area peaked in advance between spring and summer due to extreme melting events from 2017 to 2021. Meanwhile, the supraglacial lakes near the 79°N Glacier tended to expand inland during the melting season. Text glacier Greenland Ice Sheet Jakobshavn MDPI Open Access Publishing Greenland Remote Sensing 14 19 4998 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
supraglacial lake SAR deep learning Greenland |
spellingShingle |
supraglacial lake SAR deep learning Greenland Di Jiang Xinwu Li Ke Zhang Sebastián Marinsek Wen Hong Yirong Wu Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
topic_facet |
supraglacial lake SAR deep learning Greenland |
description |
With global warming, supraglacial lakes play an important role in ice sheet stability and climate change. They are not only the main factors affecting mass balance and sea-level rise but also the key units of surface runoff storage and mass loss. To automatically map the spatiotemporal distribution of supraglacial lakes in Greenland, this paper proposes an attention-based U-Net model with Sentinel-1 SAR imagery. The extraction results show that compared with the traditional network, this method obtains a higher validation coefficient, with an F1 score of 0.971, and it is spatiotemporally transferable, able to realize the extraction of supraglacial lakes in complex areas without ignoring small lakes. In addition, we conducted a case study in the Jakobshavn region and found that the supraglacial lake area peaked in advance between spring and summer due to extreme melting events from 2017 to 2021. Meanwhile, the supraglacial lakes near the 79°N Glacier tended to expand inland during the melting season. |
format |
Text |
author |
Di Jiang Xinwu Li Ke Zhang Sebastián Marinsek Wen Hong Yirong Wu |
author_facet |
Di Jiang Xinwu Li Ke Zhang Sebastián Marinsek Wen Hong Yirong Wu |
author_sort |
Di Jiang |
title |
Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
title_short |
Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
title_full |
Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
title_fullStr |
Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
title_full_unstemmed |
Automatic Supraglacial Lake Extraction in Greenland Using Sentinel-1 SAR Images and Attention-Based U-Net |
title_sort |
automatic supraglacial lake extraction in greenland using sentinel-1 sar images and attention-based u-net |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14194998 |
op_coverage |
agris |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
glacier Greenland Ice Sheet Jakobshavn |
genre_facet |
glacier Greenland Ice Sheet Jakobshavn |
op_source |
Remote Sensing; Volume 14; Issue 19; Pages: 4998 |
op_relation |
Remote Sensing Image Processing https://dx.doi.org/10.3390/rs14194998 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs14194998 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
19 |
container_start_page |
4998 |
_version_ |
1774717973116747776 |