Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow
Thwaites Glacier (TG) is one of the primary sources of ice mass loss from the West Antarctic Ice Sheet, making it a critical site for monitoring changes in the calving front location. The long duration of the Landsat mission provides a valuable opportunity to analyze over 50 years of historical imag...
Main Authors: | , , , , , |
---|---|
Format: | Conference Object |
Language: | unknown |
Published: |
2022
|
Subjects: | |
Online Access: | https://elib.dlr.de/189901/ |
id |
ftdlr:oai:elib.dlr.de:189901 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:189901 2024-05-19T07:32:31+00:00 Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow Field, Michael Snow, Tasha Abrahams, E. Lee, E. Baumhoer, Celia Siegfried, M. 2022-12 https://elib.dlr.de/189901/ unknown Field, Michael und Snow, Tasha und Abrahams, E. und Lee, E. und Baumhoer, Celia und Siegfried, M. (2022) Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow. AGU 2022, 2022-12-12 - 2022-12-16, Chicago, USA. Deutsches Fernerkundungsdatenzentrum Konferenzbeitrag NonPeerReviewed 2022 ftdlr 2024-04-25T01:03:56Z Thwaites Glacier (TG) is one of the primary sources of ice mass loss from the West Antarctic Ice Sheet, making it a critical site for monitoring changes in the calving front location. The long duration of the Landsat mission provides a valuable opportunity to analyze over 50 years of historical imagery and produce near-real-time calving front monitoring solutions for the future. Here, we have developed a tool that allows users to produce calving front maps from cloud-hosted Landsat imagery using a U-Net, a deep learning architecture commonly used for semantic segmentation. The tool utilizes open-source Python packages for rapid querying of the Landsat catalog stored in a the Spatio-Temporal Asset Catalog (STAC) standardized metadata format, and for scalable and distributed cloud processing. This cloud-based workflow will provide researchers with access to pre-trained calving front segmentation models and decades of Landsat imagery from Thwaites Glacier. This workflow may be expanded in the future to provide historical analysis and near-real-time monitoring of other important ice shelves and glaciers in Antarctica. Conference Object Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Thwaites Glacier German Aerospace Center: elib - DLR electronic library |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
unknown |
topic |
Deutsches Fernerkundungsdatenzentrum |
spellingShingle |
Deutsches Fernerkundungsdatenzentrum Field, Michael Snow, Tasha Abrahams, E. Lee, E. Baumhoer, Celia Siegfried, M. Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
topic_facet |
Deutsches Fernerkundungsdatenzentrum |
description |
Thwaites Glacier (TG) is one of the primary sources of ice mass loss from the West Antarctic Ice Sheet, making it a critical site for monitoring changes in the calving front location. The long duration of the Landsat mission provides a valuable opportunity to analyze over 50 years of historical imagery and produce near-real-time calving front monitoring solutions for the future. Here, we have developed a tool that allows users to produce calving front maps from cloud-hosted Landsat imagery using a U-Net, a deep learning architecture commonly used for semantic segmentation. The tool utilizes open-source Python packages for rapid querying of the Landsat catalog stored in a the Spatio-Temporal Asset Catalog (STAC) standardized metadata format, and for scalable and distributed cloud processing. This cloud-based workflow will provide researchers with access to pre-trained calving front segmentation models and decades of Landsat imagery from Thwaites Glacier. This workflow may be expanded in the future to provide historical analysis and near-real-time monitoring of other important ice shelves and glaciers in Antarctica. |
format |
Conference Object |
author |
Field, Michael Snow, Tasha Abrahams, E. Lee, E. Baumhoer, Celia Siegfried, M. |
author_facet |
Field, Michael Snow, Tasha Abrahams, E. Lee, E. Baumhoer, Celia Siegfried, M. |
author_sort |
Field, Michael |
title |
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
title_short |
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
title_full |
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
title_fullStr |
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
title_full_unstemmed |
Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow |
title_sort |
mapping ice shelf calving fronts at thwaites glacier using deep learning and satellite imagery in a cloud-based workflow |
publishDate |
2022 |
url |
https://elib.dlr.de/189901/ |
genre |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Thwaites Glacier |
genre_facet |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Thwaites Glacier |
op_relation |
Field, Michael und Snow, Tasha und Abrahams, E. und Lee, E. und Baumhoer, Celia und Siegfried, M. (2022) Mapping Ice Shelf Calving Fronts at Thwaites Glacier using Deep Learning and Satellite Imagery in a Cloud-Based Workflow. AGU 2022, 2022-12-12 - 2022-12-16, Chicago, USA. |
_version_ |
1799470605452443648 |