Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet
Climate change is extensively affecting ice sheets resulting in accelerating mass loss in recent decades. Assessment of this reduction and its causes is required to project future ice mass loss. Annual snow accumulation is an important component of the surface mass balance of ice sheets. While in si...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13142707 https://doaj.org/article/2ae1e73dfda2403d86b1730d1b0e0817 |
id |
ftdoajarticles:oai:doaj.org/article:2ae1e73dfda2403d86b1730d1b0e0817 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:2ae1e73dfda2403d86b1730d1b0e0817 2023-05-15T16:27:59+02:00 Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet Debvrat Varshney Maryam Rahnemoonfar Masoud Yari John Paden Oluwanisola Ibikunle Jilu Li 2021-07-01T00:00:00Z https://doi.org/10.3390/rs13142707 https://doaj.org/article/2ae1e73dfda2403d86b1730d1b0e0817 EN eng MDPI AG https://www.mdpi.com/2072-4292/13/14/2707 https://doaj.org/toc/2072-4292 doi:10.3390/rs13142707 2072-4292 https://doaj.org/article/2ae1e73dfda2403d86b1730d1b0e0817 Remote Sensing, Vol 13, Iss 2707, p 2707 (2021) ice layer thickness semantic segmentation fully convolutional networks Snow Radar Science Q article 2021 ftdoajarticles https://doi.org/10.3390/rs13142707 2022-12-31T14:16:56Z Climate change is extensively affecting ice sheets resulting in accelerating mass loss in recent decades. Assessment of this reduction and its causes is required to project future ice mass loss. Annual snow accumulation is an important component of the surface mass balance of ice sheets. While in situ snow accumulation measurements are temporally and spatially limited due to their high cost, airborne radar sounders can achieve ice sheet wide coverage by capturing and tracking annual snow layers in the radar images or echograms. In this paper, we use deep learning to uniquely identify the position of each annual snow layer in the Snow Radar echograms taken across different regions over the Greenland ice sheet. We train with more than 15,000 images generated from radar echograms and estimate the thickness of each snow layer within a mean absolute error of 0.54 to 7.28 pixels, depending on dataset. A highly precise snow layer thickness can help improve weather models and, thus, support glaciological studies. Such a well-trained deep learning model can be used with ever-growing datasets to aid in the accurate assessment of snow accumulation on the dynamically changing ice sheets. Article in Journal/Newspaper Greenland Ice Sheet Directory of Open Access Journals: DOAJ Articles Greenland Remote Sensing 13 14 2707 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
ice layer thickness semantic segmentation fully convolutional networks Snow Radar Science Q |
spellingShingle |
ice layer thickness semantic segmentation fully convolutional networks Snow Radar Science Q Debvrat Varshney Maryam Rahnemoonfar Masoud Yari John Paden Oluwanisola Ibikunle Jilu Li Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
topic_facet |
ice layer thickness semantic segmentation fully convolutional networks Snow Radar Science Q |
description |
Climate change is extensively affecting ice sheets resulting in accelerating mass loss in recent decades. Assessment of this reduction and its causes is required to project future ice mass loss. Annual snow accumulation is an important component of the surface mass balance of ice sheets. While in situ snow accumulation measurements are temporally and spatially limited due to their high cost, airborne radar sounders can achieve ice sheet wide coverage by capturing and tracking annual snow layers in the radar images or echograms. In this paper, we use deep learning to uniquely identify the position of each annual snow layer in the Snow Radar echograms taken across different regions over the Greenland ice sheet. We train with more than 15,000 images generated from radar echograms and estimate the thickness of each snow layer within a mean absolute error of 0.54 to 7.28 pixels, depending on dataset. A highly precise snow layer thickness can help improve weather models and, thus, support glaciological studies. Such a well-trained deep learning model can be used with ever-growing datasets to aid in the accurate assessment of snow accumulation on the dynamically changing ice sheets. |
format |
Article in Journal/Newspaper |
author |
Debvrat Varshney Maryam Rahnemoonfar Masoud Yari John Paden Oluwanisola Ibikunle Jilu Li |
author_facet |
Debvrat Varshney Maryam Rahnemoonfar Masoud Yari John Paden Oluwanisola Ibikunle Jilu Li |
author_sort |
Debvrat Varshney |
title |
Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
title_short |
Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
title_full |
Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
title_fullStr |
Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
title_full_unstemmed |
Deep Learning on Airborne Radar Echograms for Tracing Snow Accumulation Layers of the Greenland Ice Sheet |
title_sort |
deep learning on airborne radar echograms for tracing snow accumulation layers of the greenland ice sheet |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13142707 https://doaj.org/article/2ae1e73dfda2403d86b1730d1b0e0817 |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
Greenland Ice Sheet |
genre_facet |
Greenland Ice Sheet |
op_source |
Remote Sensing, Vol 13, Iss 2707, p 2707 (2021) |
op_relation |
https://www.mdpi.com/2072-4292/13/14/2707 https://doaj.org/toc/2072-4292 doi:10.3390/rs13142707 2072-4292 https://doaj.org/article/2ae1e73dfda2403d86b1730d1b0e0817 |
op_doi |
https://doi.org/10.3390/rs13142707 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
14 |
container_start_page |
2707 |
_version_ |
1766017601516863488 |