Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning
Sea level rise contribution from the Antarctic ice sheet is influenced by changes in glacier and ice shelf front position. Still, little is known about seasonal glacier and ice shelf front fluctuations as the manual delineation of calving fronts from remote sensing imagery is very time-consuming. Th...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2019
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs11212529 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/11/21/2529/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/11/21/2529/ 2023-08-20T04:02:31+02:00 Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning Celia A. Baumhoer Andreas J. Dietz C. Kneisel C. Kuenzer agris 2019-10-29 application/pdf https://doi.org/10.3390/rs11212529 EN eng Multidisciplinary Digital Publishing Institute https://dx.doi.org/10.3390/rs11212529 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 11; Issue 21; Pages: 2529 Antarctica coastline deep learning semantic segmentation Getz Ice Shelf calving front glacier front U-Net convolutional neural network glacier terminus Text 2019 ftmdpi https://doi.org/10.3390/rs11212529 2023-07-31T22:44:26Z Sea level rise contribution from the Antarctic ice sheet is influenced by changes in glacier and ice shelf front position. Still, little is known about seasonal glacier and ice shelf front fluctuations as the manual delineation of calving fronts from remote sensing imagery is very time-consuming. The major challenge of automatic calving front extraction is the low contrast between floating glacier and ice shelf fronts and the surrounding sea ice. Additionally, in previous decades, remote sensing imagery over the often cloud-covered Antarctic coastline was limited. Nowadays, an abundance of Sentinel-1 imagery over the Antarctic coastline exists and could be used for tracking glacier and ice shelf front movement. To exploit the available Sentinel-1 data, we developed a processing chain allowing automatic extraction of the Antarctic coastline from Seninel-1 imagery and the creation of dense time series to assess calving front change. The core of the proposed workflow is a modified version of the deep learning architecture U-Net. This convolutional neural network (CNN) performs a semantic segmentation on dual-pol Sentinel-1 data and the Antarctic TanDEM-X digital elevation model (DEM). The proposed method is tested for four training and test areas along the Antarctic coastline. The automatically extracted fronts deviate on average 78 m in training and 108 m test areas. Spatial and temporal transferability is demonstrated on an automatically extracted 15-month time series along the Getz Ice Shelf. Between May 2017 and July 2018, the fronts along the Getz Ice Shelf show mostly an advancing tendency with the fastest moving front of DeVicq Glacier with 726 ± 20 m/yr. Text Antarc* Antarctic Antarctica DeVicq Glacier Getz Ice Shelf Ice Sheet Ice Shelf Sea ice MDPI Open Access Publishing Antarctic The Antarctic Getz ENVELOPE(-145.217,-145.217,-76.550,-76.550) Getz Ice Shelf ENVELOPE(-126.500,-126.500,-74.250,-74.250) DeVicq Glacier ENVELOPE(-131.000,-131.000,-75.000,-75.000) Remote Sensing 11 21 2529 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
Antarctica coastline deep learning semantic segmentation Getz Ice Shelf calving front glacier front U-Net convolutional neural network glacier terminus |
spellingShingle |
Antarctica coastline deep learning semantic segmentation Getz Ice Shelf calving front glacier front U-Net convolutional neural network glacier terminus Celia A. Baumhoer Andreas J. Dietz C. Kneisel C. Kuenzer Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
topic_facet |
Antarctica coastline deep learning semantic segmentation Getz Ice Shelf calving front glacier front U-Net convolutional neural network glacier terminus |
description |
Sea level rise contribution from the Antarctic ice sheet is influenced by changes in glacier and ice shelf front position. Still, little is known about seasonal glacier and ice shelf front fluctuations as the manual delineation of calving fronts from remote sensing imagery is very time-consuming. The major challenge of automatic calving front extraction is the low contrast between floating glacier and ice shelf fronts and the surrounding sea ice. Additionally, in previous decades, remote sensing imagery over the often cloud-covered Antarctic coastline was limited. Nowadays, an abundance of Sentinel-1 imagery over the Antarctic coastline exists and could be used for tracking glacier and ice shelf front movement. To exploit the available Sentinel-1 data, we developed a processing chain allowing automatic extraction of the Antarctic coastline from Seninel-1 imagery and the creation of dense time series to assess calving front change. The core of the proposed workflow is a modified version of the deep learning architecture U-Net. This convolutional neural network (CNN) performs a semantic segmentation on dual-pol Sentinel-1 data and the Antarctic TanDEM-X digital elevation model (DEM). The proposed method is tested for four training and test areas along the Antarctic coastline. The automatically extracted fronts deviate on average 78 m in training and 108 m test areas. Spatial and temporal transferability is demonstrated on an automatically extracted 15-month time series along the Getz Ice Shelf. Between May 2017 and July 2018, the fronts along the Getz Ice Shelf show mostly an advancing tendency with the fastest moving front of DeVicq Glacier with 726 ± 20 m/yr. |
format |
Text |
author |
Celia A. Baumhoer Andreas J. Dietz C. Kneisel C. Kuenzer |
author_facet |
Celia A. Baumhoer Andreas J. Dietz C. Kneisel C. Kuenzer |
author_sort |
Celia A. Baumhoer |
title |
Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
title_short |
Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
title_full |
Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
title_fullStr |
Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
title_full_unstemmed |
Automated Extraction of Antarctic Glacier and Ice Shelf Fronts from Sentinel-1 Imagery Using Deep Learning |
title_sort |
automated extraction of antarctic glacier and ice shelf fronts from sentinel-1 imagery using deep learning |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2019 |
url |
https://doi.org/10.3390/rs11212529 |
op_coverage |
agris |
long_lat |
ENVELOPE(-145.217,-145.217,-76.550,-76.550) ENVELOPE(-126.500,-126.500,-74.250,-74.250) ENVELOPE(-131.000,-131.000,-75.000,-75.000) |
geographic |
Antarctic The Antarctic Getz Getz Ice Shelf DeVicq Glacier |
geographic_facet |
Antarctic The Antarctic Getz Getz Ice Shelf DeVicq Glacier |
genre |
Antarc* Antarctic Antarctica DeVicq Glacier Getz Ice Shelf Ice Sheet Ice Shelf Sea ice |
genre_facet |
Antarc* Antarctic Antarctica DeVicq Glacier Getz Ice Shelf Ice Sheet Ice Shelf Sea ice |
op_source |
Remote Sensing; Volume 11; Issue 21; Pages: 2529 |
op_relation |
https://dx.doi.org/10.3390/rs11212529 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs11212529 |
container_title |
Remote Sensing |
container_volume |
11 |
container_issue |
21 |
container_start_page |
2529 |
_version_ |
1774713004510674944 |