Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery
The fracturing of glaciers and ice shelves in Antarctica influences their dynamics, and may introduce as-yet poorly understood feedbacks and hysteresis into the ice sheet system. Therefore, data on the evolving distribution of crevasses is required to better understand the evolution of the ice sheet...
Main Authors: | , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-2023-42 https://tc.copernicus.org/preprints/tc-2023-42/ |
id |
ftcopernicus:oai:publications.copernicus.org:tcd109992 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tcd109992 2023-05-15T13:23:53+02:00 Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery Surawy-Stepney, Trystan Hogg, Anna E. Cornford, Stephen L. Hogg, David C. 2023-03-31 application/pdf https://doi.org/10.5194/tc-2023-42 https://tc.copernicus.org/preprints/tc-2023-42/ eng eng doi:10.5194/tc-2023-42 https://tc.copernicus.org/preprints/tc-2023-42/ eISSN: 1994-0424 Text 2023 ftcopernicus https://doi.org/10.5194/tc-2023-42 2023-04-03T16:23:10Z The fracturing of glaciers and ice shelves in Antarctica influences their dynamics, and may introduce as-yet poorly understood feedbacks and hysteresis into the ice sheet system. Therefore, data on the evolving distribution of crevasses is required to better understand the evolution of the ice sheet, though such data has traditionally been difficult and time consuming to generate. Here, we present an automated method of mapping crevasses on grounded and floating ice with the application of convolutional neural networks to Sentinel-1 synthetic aperture radar backscatter images acquired between 2015 and 2022. We apply this method across Antarctica to produce a 7-and-a-half year record of composite fracture maps at monthly intervals and 50 m spatial resolution, showing the distribution of crevasses around the majority of the ice sheet margin. We develop a method of quantifying changes to the density of ice shelf fractures using the timeseries of crevasse maps, and show increases in crevassing on the Thwaites and Pine Island ice shelves over the observational period, with observed changes elsewhere in the Amundsen Sea dominated by the advection of existing crevasses. Using stress fields computed using the BISICLES ice sheet model, we show that much of this structural change has occurred in strongly buttressing regions of these ice shelves, indicating a recent and ongoing link between fracturing and the developing dynamics of the Amundsen Sea Sector. Text Amundsen Sea Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Pine Island Copernicus Publications: E-Journals Antarctic Amundsen Sea |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
The fracturing of glaciers and ice shelves in Antarctica influences their dynamics, and may introduce as-yet poorly understood feedbacks and hysteresis into the ice sheet system. Therefore, data on the evolving distribution of crevasses is required to better understand the evolution of the ice sheet, though such data has traditionally been difficult and time consuming to generate. Here, we present an automated method of mapping crevasses on grounded and floating ice with the application of convolutional neural networks to Sentinel-1 synthetic aperture radar backscatter images acquired between 2015 and 2022. We apply this method across Antarctica to produce a 7-and-a-half year record of composite fracture maps at monthly intervals and 50 m spatial resolution, showing the distribution of crevasses around the majority of the ice sheet margin. We develop a method of quantifying changes to the density of ice shelf fractures using the timeseries of crevasse maps, and show increases in crevassing on the Thwaites and Pine Island ice shelves over the observational period, with observed changes elsewhere in the Amundsen Sea dominated by the advection of existing crevasses. Using stress fields computed using the BISICLES ice sheet model, we show that much of this structural change has occurred in strongly buttressing regions of these ice shelves, indicating a recent and ongoing link between fracturing and the developing dynamics of the Amundsen Sea Sector. |
format |
Text |
author |
Surawy-Stepney, Trystan Hogg, Anna E. Cornford, Stephen L. Hogg, David C. |
spellingShingle |
Surawy-Stepney, Trystan Hogg, Anna E. Cornford, Stephen L. Hogg, David C. Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
author_facet |
Surawy-Stepney, Trystan Hogg, Anna E. Cornford, Stephen L. Hogg, David C. |
author_sort |
Surawy-Stepney, Trystan |
title |
Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
title_short |
Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
title_full |
Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
title_fullStr |
Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
title_full_unstemmed |
Mapping Antarctic Crevasses and their Evolution with Deep Learning Applied to Satellite Radar Imagery |
title_sort |
mapping antarctic crevasses and their evolution with deep learning applied to satellite radar imagery |
publishDate |
2023 |
url |
https://doi.org/10.5194/tc-2023-42 https://tc.copernicus.org/preprints/tc-2023-42/ |
geographic |
Antarctic Amundsen Sea |
geographic_facet |
Antarctic Amundsen Sea |
genre |
Amundsen Sea Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Pine Island |
genre_facet |
Amundsen Sea Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Pine Island |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-2023-42 https://tc.copernicus.org/preprints/tc-2023-42/ |
op_doi |
https://doi.org/10.5194/tc-2023-42 |
_version_ |
1766376102028115968 |