Mapping the extent of giant Antarctic icebergs with deep learning
Icebergs release cold, fresh meltwater and terrigenous nutrients as they drift and melt, influencing the local ocean properties, encouraging sea ice formation and biological production. To locate and quantify the fresh water flux from Antarctic icebergs, changes in their area and thickness have to b...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-17-4675-2023 https://doaj.org/article/3093b75d2d09449292e5e1717097dfff |
id |
ftdoajarticles:oai:doaj.org/article:3093b75d2d09449292e5e1717097dfff |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:3093b75d2d09449292e5e1717097dfff 2023-12-10T09:43:01+01:00 Mapping the extent of giant Antarctic icebergs with deep learning A. Braakmann-Folgmann A. Shepherd D. Hogg E. Redmond 2023-11-01T00:00:00Z https://doi.org/10.5194/tc-17-4675-2023 https://doaj.org/article/3093b75d2d09449292e5e1717097dfff EN eng Copernicus Publications https://tc.copernicus.org/articles/17/4675/2023/tc-17-4675-2023.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-17-4675-2023 1994-0416 1994-0424 https://doaj.org/article/3093b75d2d09449292e5e1717097dfff The Cryosphere, Vol 17, Pp 4675-4690 (2023) Environmental sciences GE1-350 Geology QE1-996.5 article 2023 ftdoajarticles https://doi.org/10.5194/tc-17-4675-2023 2023-11-12T01:38:00Z Icebergs release cold, fresh meltwater and terrigenous nutrients as they drift and melt, influencing the local ocean properties, encouraging sea ice formation and biological production. To locate and quantify the fresh water flux from Antarctic icebergs, changes in their area and thickness have to be monitored along their trajectories. While the locations of large icebergs are operationally tracked by manual inspection, delineation of their extent is not. Here, we propose a U-net approach to automatically map the extent of giant icebergs in Sentinel-1 imagery. This greatly improves the efficiency compared to manual delineations, reducing the time for each outline from several minutes to less than 0.01 s. We evaluate the performance of our U-net and two state-of-the-art segmentation algorithms (Otsu and k -means) on 191 images. For icebergs larger than those covered by the training data, we find that U-net tends to miss parts. Otherwise, U-net is more robust in scenes with complex backgrounds – ignoring sea ice, smaller regions of nearby coast or other icebergs – and outperforms the other two techniques by achieving an F 1 score of 0.84 and an absolute median deviation in iceberg area of 4.1 %. Article in Journal/Newspaper Antarc* Antarctic Iceberg* Sea ice The Cryosphere Directory of Open Access Journals: DOAJ Articles Antarctic The Cryosphere 17 11 4675 4690 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Environmental sciences GE1-350 Geology QE1-996.5 |
spellingShingle |
Environmental sciences GE1-350 Geology QE1-996.5 A. Braakmann-Folgmann A. Shepherd D. Hogg E. Redmond Mapping the extent of giant Antarctic icebergs with deep learning |
topic_facet |
Environmental sciences GE1-350 Geology QE1-996.5 |
description |
Icebergs release cold, fresh meltwater and terrigenous nutrients as they drift and melt, influencing the local ocean properties, encouraging sea ice formation and biological production. To locate and quantify the fresh water flux from Antarctic icebergs, changes in their area and thickness have to be monitored along their trajectories. While the locations of large icebergs are operationally tracked by manual inspection, delineation of their extent is not. Here, we propose a U-net approach to automatically map the extent of giant icebergs in Sentinel-1 imagery. This greatly improves the efficiency compared to manual delineations, reducing the time for each outline from several minutes to less than 0.01 s. We evaluate the performance of our U-net and two state-of-the-art segmentation algorithms (Otsu and k -means) on 191 images. For icebergs larger than those covered by the training data, we find that U-net tends to miss parts. Otherwise, U-net is more robust in scenes with complex backgrounds – ignoring sea ice, smaller regions of nearby coast or other icebergs – and outperforms the other two techniques by achieving an F 1 score of 0.84 and an absolute median deviation in iceberg area of 4.1 %. |
format |
Article in Journal/Newspaper |
author |
A. Braakmann-Folgmann A. Shepherd D. Hogg E. Redmond |
author_facet |
A. Braakmann-Folgmann A. Shepherd D. Hogg E. Redmond |
author_sort |
A. Braakmann-Folgmann |
title |
Mapping the extent of giant Antarctic icebergs with deep learning |
title_short |
Mapping the extent of giant Antarctic icebergs with deep learning |
title_full |
Mapping the extent of giant Antarctic icebergs with deep learning |
title_fullStr |
Mapping the extent of giant Antarctic icebergs with deep learning |
title_full_unstemmed |
Mapping the extent of giant Antarctic icebergs with deep learning |
title_sort |
mapping the extent of giant antarctic icebergs with deep learning |
publisher |
Copernicus Publications |
publishDate |
2023 |
url |
https://doi.org/10.5194/tc-17-4675-2023 https://doaj.org/article/3093b75d2d09449292e5e1717097dfff |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic Iceberg* Sea ice The Cryosphere |
genre_facet |
Antarc* Antarctic Iceberg* Sea ice The Cryosphere |
op_source |
The Cryosphere, Vol 17, Pp 4675-4690 (2023) |
op_relation |
https://tc.copernicus.org/articles/17/4675/2023/tc-17-4675-2023.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-17-4675-2023 1994-0416 1994-0424 https://doaj.org/article/3093b75d2d09449292e5e1717097dfff |
op_doi |
https://doi.org/10.5194/tc-17-4675-2023 |
container_title |
The Cryosphere |
container_volume |
17 |
container_issue |
11 |
container_start_page |
4675 |
op_container_end_page |
4690 |
_version_ |
1784886135010361344 |