Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach

The calving fronts of many tidewater glaciers in Greenland have been undergoing strong seasonal and interannual fluctuations. Conventionally, calving front positions have been manually delineated from remote sensing images. But manual practices can be labor-intensive and time-consuming, particularly...

Full description

Bibliographic Details
Published in:The Cryosphere
Main Authors: E. Zhang, L. Liu, L. Huang
Format: Article in Journal/Newspaper
Language:English
Published: Copernicus Publications 2019
Subjects:
Online Access:https://doi.org/10.5194/tc-13-1729-2019
https://doaj.org/article/40d0c4478d6c4c4785c38188f1cde657
_version_ 1821528463367995392
author E. Zhang
L. Liu
L. Huang
author_facet E. Zhang
L. Liu
L. Huang
author_sort E. Zhang
collection Directory of Open Access Journals: DOAJ Articles
container_issue 6
container_start_page 1729
container_title The Cryosphere
container_volume 13
description The calving fronts of many tidewater glaciers in Greenland have been undergoing strong seasonal and interannual fluctuations. Conventionally, calving front positions have been manually delineated from remote sensing images. But manual practices can be labor-intensive and time-consuming, particularly when processing a large number of images taken over decades and covering large areas with many glaciers, such as Greenland. Applying U-Net, a deep learning architecture, to multitemporal synthetic aperture radar images taken by the TerraSAR-X satellite, we here automatically delineate the calving front positions of Jakobshavn Isbræ from 2009 to 2015. Our results are consistent with the manually delineated products generated by the Greenland Ice Sheet Climate Change Initiative project. We show that the calving fronts of Jakobshavn's two main branches retreated at mean rates of <math xmlns="http://www.w3.org/1998/Math/MathML" id="M1" display="inline" overflow="scroll" dspmath="mathml"><mrow><mo>-</mo><mn mathvariant="normal">117</mn><mo>±</mo><mn mathvariant="normal">1</mn></mrow></math> <svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="46pt" height="10pt" class="svg-formula" dspmath="mathimg" md5hash="748ecebd20d29add9c85dda21961b026"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="tc-13-1729-2019-ie00001.svg" width="46pt" height="10pt" src="tc-13-1729-2019-ie00001.png"/></svg:svg> and <math xmlns="http://www.w3.org/1998/Math/MathML" id="M2" display="inline" overflow="scroll" dspmath="mathml"><mrow><mo>-</mo><mn mathvariant="normal">157</mn><mo>±</mo><mn mathvariant="normal">1</mn></mrow></math> <svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="46pt" height="10pt" class="svg-formula" dspmath="mathimg" md5hash="a87faaa2796741d1190a8d8afebc05f5"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" ...
format Article in Journal/Newspaper
genre Greenland
Ice Sheet
Jakobshavn
Jakobshavn isbræ
The Cryosphere
genre_facet Greenland
Ice Sheet
Jakobshavn
Jakobshavn isbræ
The Cryosphere
geographic Greenland
Jakobshavn Isbræ
geographic_facet Greenland
Jakobshavn Isbræ
id ftdoajarticles:oai:doaj.org/article:40d0c4478d6c4c4785c38188f1cde657
institution Open Polar
language English
long_lat ENVELOPE(-49.917,-49.917,69.167,69.167)
op_collection_id ftdoajarticles
op_container_end_page 1741
op_doi https://doi.org/10.5194/tc-13-1729-2019
op_relation https://www.the-cryosphere.net/13/1729/2019/tc-13-1729-2019.pdf
https://doaj.org/toc/1994-0416
https://doaj.org/toc/1994-0424
doi:10.5194/tc-13-1729-2019
1994-0416
1994-0424
https://doaj.org/article/40d0c4478d6c4c4785c38188f1cde657
op_source The Cryosphere, Vol 13, Pp 1729-1741 (2019)
publishDate 2019
publisher Copernicus Publications
record_format openpolar
spelling ftdoajarticles:oai:doaj.org/article:40d0c4478d6c4c4785c38188f1cde657 2025-01-16T22:10:06+00:00 Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach E. Zhang L. Liu L. Huang 2019-06-01T00:00:00Z https://doi.org/10.5194/tc-13-1729-2019 https://doaj.org/article/40d0c4478d6c4c4785c38188f1cde657 EN eng Copernicus Publications https://www.the-cryosphere.net/13/1729/2019/tc-13-1729-2019.pdf https://doaj.org/toc/1994-0416 https://doaj.org/toc/1994-0424 doi:10.5194/tc-13-1729-2019 1994-0416 1994-0424 https://doaj.org/article/40d0c4478d6c4c4785c38188f1cde657 The Cryosphere, Vol 13, Pp 1729-1741 (2019) Environmental sciences GE1-350 Geology QE1-996.5 article 2019 ftdoajarticles https://doi.org/10.5194/tc-13-1729-2019 2022-12-31T15:58:10Z The calving fronts of many tidewater glaciers in Greenland have been undergoing strong seasonal and interannual fluctuations. Conventionally, calving front positions have been manually delineated from remote sensing images. But manual practices can be labor-intensive and time-consuming, particularly when processing a large number of images taken over decades and covering large areas with many glaciers, such as Greenland. Applying U-Net, a deep learning architecture, to multitemporal synthetic aperture radar images taken by the TerraSAR-X satellite, we here automatically delineate the calving front positions of Jakobshavn Isbræ from 2009 to 2015. Our results are consistent with the manually delineated products generated by the Greenland Ice Sheet Climate Change Initiative project. We show that the calving fronts of Jakobshavn's two main branches retreated at mean rates of <math xmlns="http://www.w3.org/1998/Math/MathML" id="M1" display="inline" overflow="scroll" dspmath="mathml"><mrow><mo>-</mo><mn mathvariant="normal">117</mn><mo>±</mo><mn mathvariant="normal">1</mn></mrow></math> <svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="46pt" height="10pt" class="svg-formula" dspmath="mathimg" md5hash="748ecebd20d29add9c85dda21961b026"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="tc-13-1729-2019-ie00001.svg" width="46pt" height="10pt" src="tc-13-1729-2019-ie00001.png"/></svg:svg> and <math xmlns="http://www.w3.org/1998/Math/MathML" id="M2" display="inline" overflow="scroll" dspmath="mathml"><mrow><mo>-</mo><mn mathvariant="normal">157</mn><mo>±</mo><mn mathvariant="normal">1</mn></mrow></math> <svg:svg xmlns:svg="http://www.w3.org/2000/svg" width="46pt" height="10pt" class="svg-formula" dspmath="mathimg" md5hash="a87faaa2796741d1190a8d8afebc05f5"><svg:image xmlns:xlink="http://www.w3.org/1999/xlink" ... Article in Journal/Newspaper Greenland Ice Sheet Jakobshavn Jakobshavn isbræ The Cryosphere Directory of Open Access Journals: DOAJ Articles Greenland Jakobshavn Isbræ ENVELOPE(-49.917,-49.917,69.167,69.167) The Cryosphere 13 6 1729 1741
spellingShingle Environmental sciences
GE1-350
Geology
QE1-996.5
E. Zhang
L. Liu
L. Huang
Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title_full Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title_fullStr Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title_full_unstemmed Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title_short Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach
title_sort automatically delineating the calving front of jakobshavn isbræ from multitemporal terrasar-x images: a deep learning approach
topic Environmental sciences
GE1-350
Geology
QE1-996.5
topic_facet Environmental sciences
GE1-350
Geology
QE1-996.5
url https://doi.org/10.5194/tc-13-1729-2019
https://doaj.org/article/40d0c4478d6c4c4785c38188f1cde657