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 stability. Hence, data on the evolving distribution of crevasses are required to better understand the evolution of the ice sheet, though such data have traditionally been difficult and time-consuming to generate....

Full description

Bibliographic Details
Published in:The Cryosphere
Main Authors: Surawy-Stepney, Trystan, Hogg, Anna e., Cornford, Stephen l., Hogg, David C.
Format: Article in Journal/Newspaper
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/1983/f231c2fd-46cc-4973-a7d6-f757f4555cc7
https://research-information.bris.ac.uk/en/publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7
https://doi.org/10.5194/tc-17-4421-2023
https://tc.copernicus.org/articles/17/4421/2023/
id ftubristolcris:oai:research-information.bris.ac.uk:publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7
record_format openpolar
spelling ftubristolcris:oai:research-information.bris.ac.uk:publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7 2024-04-28T07:54:41+00:00 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. 2023-10-19 https://hdl.handle.net/1983/f231c2fd-46cc-4973-a7d6-f757f4555cc7 https://research-information.bris.ac.uk/en/publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7 https://doi.org/10.5194/tc-17-4421-2023 https://tc.copernicus.org/articles/17/4421/2023/ eng eng https://research-information.bris.ac.uk/en/publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7 info:eu-repo/semantics/openAccess Surawy-Stepney , T , Hogg , A E , Cornford , S L & Hogg , D C 2023 , ' Mapping Antarctic crevasses and their evolution with deep learning applied to satellite radar imagery ' , The Cryosphere , vol. 17 , no. 10 , pp. 4421-4445 . https://doi.org/10.5194/tc-17-4421-2023 article 2023 ftubristolcris https://doi.org/10.5194/tc-17-4421-2023 2024-04-10T00:17:48Z The fracturing of glaciers and ice shelves in Antarctica influences their dynamics and stability. Hence, data on the evolving distribution of crevasses are required to better understand the evolution of the ice sheet, though such data have 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 data. We apply this method across Antarctica to images acquired between 2015 and 2022, producing a 7.5-year record of composite fracture maps at monthly intervals and 50 m spatial resolution and 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 a time series of crevasse maps and show increases in crevassing on 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 buttressing regions of these ice shelves, indicating a recent and ongoing link between fracturing and the developing dynamics of the Amundsen Sea sector. Article in Journal/Newspaper Amundsen Sea Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Pine Island The Cryosphere University of Bristol: Bristol Research The Cryosphere 17 10 4421 4445
institution Open Polar
collection University of Bristol: Bristol Research
op_collection_id ftubristolcris
language English
description The fracturing of glaciers and ice shelves in Antarctica influences their dynamics and stability. Hence, data on the evolving distribution of crevasses are required to better understand the evolution of the ice sheet, though such data have 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 data. We apply this method across Antarctica to images acquired between 2015 and 2022, producing a 7.5-year record of composite fracture maps at monthly intervals and 50 m spatial resolution and 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 a time series of crevasse maps and show increases in crevassing on 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 buttressing regions of these ice shelves, indicating a recent and ongoing link between fracturing and the developing dynamics of the Amundsen Sea sector.
format Article in Journal/Newspaper
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://hdl.handle.net/1983/f231c2fd-46cc-4973-a7d6-f757f4555cc7
https://research-information.bris.ac.uk/en/publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7
https://doi.org/10.5194/tc-17-4421-2023
https://tc.copernicus.org/articles/17/4421/2023/
genre Amundsen Sea
Antarc*
Antarctic
Antarctica
Ice Sheet
Ice Shelf
Ice Shelves
Pine Island
The Cryosphere
genre_facet Amundsen Sea
Antarc*
Antarctic
Antarctica
Ice Sheet
Ice Shelf
Ice Shelves
Pine Island
The Cryosphere
op_source Surawy-Stepney , T , Hogg , A E , Cornford , S L & Hogg , D C 2023 , ' Mapping Antarctic crevasses and their evolution with deep learning applied to satellite radar imagery ' , The Cryosphere , vol. 17 , no. 10 , pp. 4421-4445 . https://doi.org/10.5194/tc-17-4421-2023
op_relation https://research-information.bris.ac.uk/en/publications/f231c2fd-46cc-4973-a7d6-f757f4555cc7
op_rights info:eu-repo/semantics/openAccess
op_doi https://doi.org/10.5194/tc-17-4421-2023
container_title The Cryosphere
container_volume 17
container_issue 10
container_start_page 4421
op_container_end_page 4445
_version_ 1797576583804878848