Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning.
Delineating the grounding line of marine-terminating glaciers-where ice starts to become afloat in ocean waters-is crucial for measuring and understanding ice sheet mass balance, glacier dynamics, and their contributions to sea level rise. This task has been previously done using time-consuming, mos...
Main Authors: | , , , , , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
eScholarship, University of California
2021
|
Subjects: | |
Online Access: | https://escholarship.org/uc/item/2qm242px |
id |
ftcdlib:oai:escholarship.org/ark:/13030/qt2qm242px |
---|---|
record_format |
openpolar |
spelling |
ftcdlib:oai:escholarship.org/ark:/13030/qt2qm242px 2023-05-15T14:04:04+02:00 Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. Mohajerani, Yara Jeong, Seongsu Scheuchl, Bernd Velicogna, Isabella Rignot, Eric Milillo, Pietro 4992 2021-03-02 application/pdf https://escholarship.org/uc/item/2qm242px unknown eScholarship, University of California qt2qm242px https://escholarship.org/uc/item/2qm242px public Scientific reports, vol 11, iss 1 article 2021 ftcdlib 2021-05-30T17:54:37Z Delineating the grounding line of marine-terminating glaciers-where ice starts to become afloat in ocean waters-is crucial for measuring and understanding ice sheet mass balance, glacier dynamics, and their contributions to sea level rise. This task has been previously done using time-consuming, mostly-manual digitizations of differential interferometric synthetic-aperture radar interferograms by human experts. This approach is no longer viable with a fast-growing set of satellite observations and the need to establish time series over entire continents with quantified uncertainties. We present a fully-convolutional neural network with parallel atrous convolutional layers and asymmetric encoder/decoder components that automatically delineates grounding lines at a large scale, efficiently, and accompanied by uncertainty estimates. Our procedure detects grounding lines within 232m in 100-m posting interferograms, which is comparable to the performance achieved by human experts. We also find value in the machine learning approach in situations that even challenge human experts. We use this approach to map the tidal-induced variability in grounding line position around Antarctica in 22,935 interferograms from year 2018. Along the Getz Ice Shelf, in West Antarctica, we demonstrate that grounding zones are one order magnitude (13.3±3.9) wider than expected from hydrostatic equilibrium, which justifies the need to map grounding lines repeatedly and comprehensively to inform numerical models. Article in Journal/Newspaper Antarc* Antarctica Getz Ice Shelf Ice Sheet Ice Shelf West Antarctica University of California: eScholarship Getz ENVELOPE(-145.217,-145.217,-76.550,-76.550) Getz Ice Shelf ENVELOPE(-126.500,-126.500,-74.250,-74.250) West Antarctica |
institution |
Open Polar |
collection |
University of California: eScholarship |
op_collection_id |
ftcdlib |
language |
unknown |
description |
Delineating the grounding line of marine-terminating glaciers-where ice starts to become afloat in ocean waters-is crucial for measuring and understanding ice sheet mass balance, glacier dynamics, and their contributions to sea level rise. This task has been previously done using time-consuming, mostly-manual digitizations of differential interferometric synthetic-aperture radar interferograms by human experts. This approach is no longer viable with a fast-growing set of satellite observations and the need to establish time series over entire continents with quantified uncertainties. We present a fully-convolutional neural network with parallel atrous convolutional layers and asymmetric encoder/decoder components that automatically delineates grounding lines at a large scale, efficiently, and accompanied by uncertainty estimates. Our procedure detects grounding lines within 232m in 100-m posting interferograms, which is comparable to the performance achieved by human experts. We also find value in the machine learning approach in situations that even challenge human experts. We use this approach to map the tidal-induced variability in grounding line position around Antarctica in 22,935 interferograms from year 2018. Along the Getz Ice Shelf, in West Antarctica, we demonstrate that grounding zones are one order magnitude (13.3±3.9) wider than expected from hydrostatic equilibrium, which justifies the need to map grounding lines repeatedly and comprehensively to inform numerical models. |
format |
Article in Journal/Newspaper |
author |
Mohajerani, Yara Jeong, Seongsu Scheuchl, Bernd Velicogna, Isabella Rignot, Eric Milillo, Pietro |
spellingShingle |
Mohajerani, Yara Jeong, Seongsu Scheuchl, Bernd Velicogna, Isabella Rignot, Eric Milillo, Pietro Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
author_facet |
Mohajerani, Yara Jeong, Seongsu Scheuchl, Bernd Velicogna, Isabella Rignot, Eric Milillo, Pietro |
author_sort |
Mohajerani, Yara |
title |
Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
title_short |
Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
title_full |
Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
title_fullStr |
Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
title_full_unstemmed |
Automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
title_sort |
automatic delineation of glacier grounding lines in differential interferometric synthetic-aperture radar data using deep learning. |
publisher |
eScholarship, University of California |
publishDate |
2021 |
url |
https://escholarship.org/uc/item/2qm242px |
op_coverage |
4992 |
long_lat |
ENVELOPE(-145.217,-145.217,-76.550,-76.550) ENVELOPE(-126.500,-126.500,-74.250,-74.250) |
geographic |
Getz Getz Ice Shelf West Antarctica |
geographic_facet |
Getz Getz Ice Shelf West Antarctica |
genre |
Antarc* Antarctica Getz Ice Shelf Ice Sheet Ice Shelf West Antarctica |
genre_facet |
Antarc* Antarctica Getz Ice Shelf Ice Sheet Ice Shelf West Antarctica |
op_source |
Scientific reports, vol 11, iss 1 |
op_relation |
qt2qm242px https://escholarship.org/uc/item/2qm242px |
op_rights |
public |
_version_ |
1766275042453225472 |