A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning
While the influence of surface melt on Antarctic ice shelf stability can be large, the duration and affected area of melt events are often small. Therefore, melt events are difficult to capture with remote sensing, as satellite sensors always face the trade-off between spatial and temporal resolutio...
Main Authors: | , , , , , , , , |
---|---|
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://dspace.library.uu.nl/handle/1874/438407 |
id |
ftunivutrecht:oai:dspace.library.uu.nl:1874/438407 |
---|---|
record_format |
openpolar |
spelling |
ftunivutrecht:oai:dspace.library.uu.nl:1874/438407 2024-05-19T07:32:30+00:00 A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning de Roda Husman, Sophie Lhermitte, Stef Bolibar, Jordi Izeboud, Maaike Hu, Zhongyang Shukla, Shashwat van der Meer, Marijn Long, David Wouters, Bert Sub Dynamics Meteorology Marine and Atmospheric Research 2024-02-01 application/pdf https://dspace.library.uu.nl/handle/1874/438407 en eng 0034-4257 https://dspace.library.uu.nl/handle/1874/438407 info:eu-repo/semantics/OpenAccess Antarctica Enhanced resolution Google Earth Engine Machine learning Microwave remote sensing Surface melt U-Net Soil Science Geology Computers in Earth Sciences Article 2024 ftunivutrecht 2024-04-29T15:16:39Z While the influence of surface melt on Antarctic ice shelf stability can be large, the duration and affected area of melt events are often small. Therefore, melt events are difficult to capture with remote sensing, as satellite sensors always face the trade-off between spatial and temporal resolution. To overcome this limitation, we developed UMelt: a surface melt record for all Antarctic ice shelves with a high spatial (500 m) and high temporal (12 h) resolution for the period 2016–2021. Our approach is based on a deep learning model, specifically a U-Net, which was developed in Google Earth Engine. The U-Net combines microwave remote sensing observations from three sources: Sentinel-1, Special Sensor Microwave Imager/Sounder (SSMIS), and Advanced Scatterometer (ASCAT). The U-Net was trained on the Shackleton Ice Shelf for melt seasons 2017–2021, using the fine-scale melt patterns of Sentinel-1 as reference data and SSMIS, ASCAT, a digital elevation model, and multi-year Sentinel-1 melt fraction as predictors. The trained U-Net performed well on the Shackelton Ice Shelf for test melt season 2016–2017 (accuracy: 91.3%; F1-score: 86.9%), and the Larsen C Ice Shelf, which was not considered during training (accuracy: 91.0%; F1-score: 89.3%). Using the trained U-Net model, we have successfully developed the UMelt record. UMelt allows Antarctic-wide surface melt to be detected at a small scale while preserving a high temporal resolution, which could lead to new insights into the response of ice shelves to a changing atmospheric forcing. Article in Journal/Newspaper Antarc* Antarctic Antarctica Ice Shelf Ice Shelves Shackleton Ice Shelf Utrecht University Repository |
institution |
Open Polar |
collection |
Utrecht University Repository |
op_collection_id |
ftunivutrecht |
language |
English |
topic |
Antarctica Enhanced resolution Google Earth Engine Machine learning Microwave remote sensing Surface melt U-Net Soil Science Geology Computers in Earth Sciences |
spellingShingle |
Antarctica Enhanced resolution Google Earth Engine Machine learning Microwave remote sensing Surface melt U-Net Soil Science Geology Computers in Earth Sciences de Roda Husman, Sophie Lhermitte, Stef Bolibar, Jordi Izeboud, Maaike Hu, Zhongyang Shukla, Shashwat van der Meer, Marijn Long, David Wouters, Bert A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
topic_facet |
Antarctica Enhanced resolution Google Earth Engine Machine learning Microwave remote sensing Surface melt U-Net Soil Science Geology Computers in Earth Sciences |
description |
While the influence of surface melt on Antarctic ice shelf stability can be large, the duration and affected area of melt events are often small. Therefore, melt events are difficult to capture with remote sensing, as satellite sensors always face the trade-off between spatial and temporal resolution. To overcome this limitation, we developed UMelt: a surface melt record for all Antarctic ice shelves with a high spatial (500 m) and high temporal (12 h) resolution for the period 2016–2021. Our approach is based on a deep learning model, specifically a U-Net, which was developed in Google Earth Engine. The U-Net combines microwave remote sensing observations from three sources: Sentinel-1, Special Sensor Microwave Imager/Sounder (SSMIS), and Advanced Scatterometer (ASCAT). The U-Net was trained on the Shackleton Ice Shelf for melt seasons 2017–2021, using the fine-scale melt patterns of Sentinel-1 as reference data and SSMIS, ASCAT, a digital elevation model, and multi-year Sentinel-1 melt fraction as predictors. The trained U-Net performed well on the Shackelton Ice Shelf for test melt season 2016–2017 (accuracy: 91.3%; F1-score: 86.9%), and the Larsen C Ice Shelf, which was not considered during training (accuracy: 91.0%; F1-score: 89.3%). Using the trained U-Net model, we have successfully developed the UMelt record. UMelt allows Antarctic-wide surface melt to be detected at a small scale while preserving a high temporal resolution, which could lead to new insights into the response of ice shelves to a changing atmospheric forcing. |
author2 |
Sub Dynamics Meteorology Marine and Atmospheric Research |
format |
Article in Journal/Newspaper |
author |
de Roda Husman, Sophie Lhermitte, Stef Bolibar, Jordi Izeboud, Maaike Hu, Zhongyang Shukla, Shashwat van der Meer, Marijn Long, David Wouters, Bert |
author_facet |
de Roda Husman, Sophie Lhermitte, Stef Bolibar, Jordi Izeboud, Maaike Hu, Zhongyang Shukla, Shashwat van der Meer, Marijn Long, David Wouters, Bert |
author_sort |
de Roda Husman, Sophie |
title |
A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
title_short |
A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
title_full |
A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
title_fullStr |
A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
title_full_unstemmed |
A high-resolution record of surface melt on Antarctic ice shelves using multi-source remote sensing data and deep learning |
title_sort |
high-resolution record of surface melt on antarctic ice shelves using multi-source remote sensing data and deep learning |
publishDate |
2024 |
url |
https://dspace.library.uu.nl/handle/1874/438407 |
genre |
Antarc* Antarctic Antarctica Ice Shelf Ice Shelves Shackleton Ice Shelf |
genre_facet |
Antarc* Antarctic Antarctica Ice Shelf Ice Shelves Shackleton Ice Shelf |
op_relation |
0034-4257 https://dspace.library.uu.nl/handle/1874/438407 |
op_rights |
info:eu-repo/semantics/OpenAccess |
_version_ |
1799470583501553664 |