AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning
Ice sheet marine margins via outlet glaciers are susceptible to climate change and are expected to respond through retreat, steepening, and acceleration, although with significant spatial heterogeneity. However, research on ice–ocean interactions has continued to rely on decentralized, manual mappin...
Main Authors: | , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://doi.org/10.5194/egusphere-2022-1095 https://egusphere.copernicus.org/preprints/2022/egusphere-2022-1095/ |
id |
ftcopernicus:oai:publications.copernicus.org:egusphere107096 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:egusphere107096 2023-09-26T15:18:08+02:00 AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning Zhang, Enze Catania, Ginny Trugman, Daniel 2023-08-24 application/pdf https://doi.org/10.5194/egusphere-2022-1095 https://egusphere.copernicus.org/preprints/2022/egusphere-2022-1095/ eng eng doi:10.5194/egusphere-2022-1095 https://egusphere.copernicus.org/preprints/2022/egusphere-2022-1095/ eISSN: Text 2023 ftcopernicus https://doi.org/10.5194/egusphere-2022-1095 2023-08-28T16:24:16Z Ice sheet marine margins via outlet glaciers are susceptible to climate change and are expected to respond through retreat, steepening, and acceleration, although with significant spatial heterogeneity. However, research on ice–ocean interactions has continued to rely on decentralized, manual mapping of features at the ice–ocean interface, impeding progress in understanding the response of glaciers and ice sheets to climate change. The proliferation of remote-sensing images lays the foundation for a better understanding of ice–ocean interactions and also necessitates the automation of terminus delineation. While deep learning (DL) techniques have already been applied to automate the terminus delineation, none involve sufficient quality control and automation to enable DL applications to “big data” problems in glaciology. Here, we build on established methods to create a fully automated pipeline for terminus delineation that makes several advances over prior studies. First, we leverage existing manually picked terminus traces (16 440) as training data to significantly improve the generalization of the DL algorithm. Second, we employ a rigorous automated screening module to enhance the data product quality. Third, we perform a thoroughly automated uncertainty quantification on the resulting data. Finally, we automate several steps in the pipeline allowing data to be regularly delivered to public databases with increased frequency. The automation level of our method ensures the sustainability of terminus data production. Altogether, these improvements produce the most complete and high-quality record of terminus data that exists for the Greenland Ice Sheet (GrIS). Our pipeline has successfully picked 278 239 termini for 295 glaciers in Greenland from Landsat 5, 7, 8 and Sentinel-1 and Sentinel-2 images, spanning the period from 1984 to 2021. The pipeline has been tested on glaciers in Greenland with an error of 79 m. The high sampling frequency and the controlled quality of our terminus data will enable better ... Text glacier Greenland Ice Sheet Copernicus Publications: E-Journals Greenland |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Ice sheet marine margins via outlet glaciers are susceptible to climate change and are expected to respond through retreat, steepening, and acceleration, although with significant spatial heterogeneity. However, research on ice–ocean interactions has continued to rely on decentralized, manual mapping of features at the ice–ocean interface, impeding progress in understanding the response of glaciers and ice sheets to climate change. The proliferation of remote-sensing images lays the foundation for a better understanding of ice–ocean interactions and also necessitates the automation of terminus delineation. While deep learning (DL) techniques have already been applied to automate the terminus delineation, none involve sufficient quality control and automation to enable DL applications to “big data” problems in glaciology. Here, we build on established methods to create a fully automated pipeline for terminus delineation that makes several advances over prior studies. First, we leverage existing manually picked terminus traces (16 440) as training data to significantly improve the generalization of the DL algorithm. Second, we employ a rigorous automated screening module to enhance the data product quality. Third, we perform a thoroughly automated uncertainty quantification on the resulting data. Finally, we automate several steps in the pipeline allowing data to be regularly delivered to public databases with increased frequency. The automation level of our method ensures the sustainability of terminus data production. Altogether, these improvements produce the most complete and high-quality record of terminus data that exists for the Greenland Ice Sheet (GrIS). Our pipeline has successfully picked 278 239 termini for 295 glaciers in Greenland from Landsat 5, 7, 8 and Sentinel-1 and Sentinel-2 images, spanning the period from 1984 to 2021. The pipeline has been tested on glaciers in Greenland with an error of 79 m. The high sampling frequency and the controlled quality of our terminus data will enable better ... |
format |
Text |
author |
Zhang, Enze Catania, Ginny Trugman, Daniel |
spellingShingle |
Zhang, Enze Catania, Ginny Trugman, Daniel AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
author_facet |
Zhang, Enze Catania, Ginny Trugman, Daniel |
author_sort |
Zhang, Enze |
title |
AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
title_short |
AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
title_full |
AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
title_fullStr |
AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
title_full_unstemmed |
AutoTerm: A "big data" repository of Greenland glacier termini delineated using deep learning |
title_sort |
autoterm: a "big data" repository of greenland glacier termini delineated using deep learning |
publishDate |
2023 |
url |
https://doi.org/10.5194/egusphere-2022-1095 https://egusphere.copernicus.org/preprints/2022/egusphere-2022-1095/ |
geographic |
Greenland |
geographic_facet |
Greenland |
genre |
glacier Greenland Ice Sheet |
genre_facet |
glacier Greenland Ice Sheet |
op_source |
eISSN: |
op_relation |
doi:10.5194/egusphere-2022-1095 https://egusphere.copernicus.org/preprints/2022/egusphere-2022-1095/ |
op_doi |
https://doi.org/10.5194/egusphere-2022-1095 |
_version_ |
1778140138691362816 |