Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf
Accurately estimating the surface melt volume of the Antarctic Ice Sheet is challenging and has hitherto relied on climate modeling or observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate t...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Copernicus Publications
2021
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-15-5639-2021 https://noa.gwlb.de/receive/cop_mods_00059278 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00058885/tc-15-5639-2021.pdf https://tc.copernicus.org/articles/15/5639/2021/tc-15-5639-2021.pdf |
id |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00059278 |
---|---|
record_format |
openpolar |
spelling |
ftnonlinearchiv:oai:noa.gwlb.de:cop_mods_00059278 2023-05-15T13:37:33+02:00 Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike van den Broeke, Michiel 2021-12 electronic https://doi.org/10.5194/tc-15-5639-2021 https://noa.gwlb.de/receive/cop_mods_00059278 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00058885/tc-15-5639-2021.pdf https://tc.copernicus.org/articles/15/5639/2021/tc-15-5639-2021.pdf eng eng Copernicus Publications The Cryosphere -- ˜Theœ Cryosphere -- http://www.bibliothek.uni-regensburg.de/ezeit/?2393169 -- http://www.the-cryosphere.net/ -- 1994-0424 https://doi.org/10.5194/tc-15-5639-2021 https://noa.gwlb.de/receive/cop_mods_00059278 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00058885/tc-15-5639-2021.pdf https://tc.copernicus.org/articles/15/5639/2021/tc-15-5639-2021.pdf https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess CC-BY article Verlagsveröffentlichung article Text doc-type:article 2021 ftnonlinearchiv https://doi.org/10.5194/tc-15-5639-2021 2022-02-08T22:32:40Z Accurately estimating the surface melt volume of the Antarctic Ice Sheet is challenging and has hitherto relied on climate modeling or observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate the potential of improving surface melt simulations with a regional climate model by deploying a deep learning model. A deep-learning-based framework has been developed to correct surface melt from the regional atmospheric climate model version 2.3p2 (RACMO2), using meteorological observations from automatic weather stations (AWSs) and surface albedo from satellite imagery. The framework includes three steps: (1) training a deep multilayer perceptron (MLP) model using AWS observations, (2) correcting Moderate Resolution Imaging Spectroradiometer (MODIS) albedo observations, and (3) using these two to correct the RACMO2 surface melt simulations. Using observations from three AWSs at the Larsen B and C ice shelves, Antarctica, cross-validation shows a high accuracy (root-mean-square error of 0.95 mm w.e. d−1, mean absolute error of 0.42 mm w.e. d−1, and a coefficient of determination of 0.95). Moreover, the deep MLP model outperforms conventional machine learning models and a shallow MLP model. When applying the trained deep MLP model over the entire Larsen Ice Shelf, the resulting corrected RACMO2 surface melt shows a better correlation with the AWS observations for two out of three AWSs. However, for one location (AWS 18), the deep MLP model does not show improved agreement with AWS observations; this is likely because surface melt is largely driven by factors (e.g., air temperature, topography, katabatic wind) other than albedo within the corresponding coarse-resolution model pixels. Our study demonstrates the opportunity to improve surface melt simulations using deep learning combined with satellite albedo observations. However, more work is required to refine the method, especially for complicated and heterogeneous terrains. Article in Journal/Newspaper Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Larsen Ice Shelf The Cryosphere Niedersächsisches Online-Archiv NOA Antarctic Larsen Ice Shelf ENVELOPE(-62.500,-62.500,-67.500,-67.500) The Antarctic The Cryosphere 15 12 5639 5658 |
institution |
Open Polar |
collection |
Niedersächsisches Online-Archiv NOA |
op_collection_id |
ftnonlinearchiv |
language |
English |
topic |
article Verlagsveröffentlichung |
spellingShingle |
article Verlagsveröffentlichung Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike van den Broeke, Michiel Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
topic_facet |
article Verlagsveröffentlichung |
description |
Accurately estimating the surface melt volume of the Antarctic Ice Sheet is challenging and has hitherto relied on climate modeling or observations from satellite remote sensing. Each of these methods has its limitations, especially in regions with high surface melt. This study aims to demonstrate the potential of improving surface melt simulations with a regional climate model by deploying a deep learning model. A deep-learning-based framework has been developed to correct surface melt from the regional atmospheric climate model version 2.3p2 (RACMO2), using meteorological observations from automatic weather stations (AWSs) and surface albedo from satellite imagery. The framework includes three steps: (1) training a deep multilayer perceptron (MLP) model using AWS observations, (2) correcting Moderate Resolution Imaging Spectroradiometer (MODIS) albedo observations, and (3) using these two to correct the RACMO2 surface melt simulations. Using observations from three AWSs at the Larsen B and C ice shelves, Antarctica, cross-validation shows a high accuracy (root-mean-square error of 0.95 mm w.e. d−1, mean absolute error of 0.42 mm w.e. d−1, and a coefficient of determination of 0.95). Moreover, the deep MLP model outperforms conventional machine learning models and a shallow MLP model. When applying the trained deep MLP model over the entire Larsen Ice Shelf, the resulting corrected RACMO2 surface melt shows a better correlation with the AWS observations for two out of three AWSs. However, for one location (AWS 18), the deep MLP model does not show improved agreement with AWS observations; this is likely because surface melt is largely driven by factors (e.g., air temperature, topography, katabatic wind) other than albedo within the corresponding coarse-resolution model pixels. Our study demonstrates the opportunity to improve surface melt simulations using deep learning combined with satellite albedo observations. However, more work is required to refine the method, especially for complicated and heterogeneous terrains. |
format |
Article in Journal/Newspaper |
author |
Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike van den Broeke, Michiel |
author_facet |
Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike van den Broeke, Michiel |
author_sort |
Hu, Zhongyang |
title |
Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
title_short |
Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
title_full |
Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
title_fullStr |
Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
title_full_unstemmed |
Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
title_sort |
improving surface melt estimation over the antarctic ice sheet using deep learning: a proof of concept over the larsen ice shelf |
publisher |
Copernicus Publications |
publishDate |
2021 |
url |
https://doi.org/10.5194/tc-15-5639-2021 https://noa.gwlb.de/receive/cop_mods_00059278 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00058885/tc-15-5639-2021.pdf https://tc.copernicus.org/articles/15/5639/2021/tc-15-5639-2021.pdf |
long_lat |
ENVELOPE(-62.500,-62.500,-67.500,-67.500) |
geographic |
Antarctic Larsen Ice Shelf The Antarctic |
geographic_facet |
Antarctic Larsen Ice Shelf The Antarctic |
genre |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Larsen Ice Shelf The Cryosphere |
genre_facet |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Larsen Ice Shelf The Cryosphere |
op_relation |
The Cryosphere -- ˜Theœ Cryosphere -- http://www.bibliothek.uni-regensburg.de/ezeit/?2393169 -- http://www.the-cryosphere.net/ -- 1994-0424 https://doi.org/10.5194/tc-15-5639-2021 https://noa.gwlb.de/receive/cop_mods_00059278 https://noa.gwlb.de/servlets/MCRFileNodeServlet/cop_derivate_00058885/tc-15-5639-2021.pdf https://tc.copernicus.org/articles/15/5639/2021/tc-15-5639-2021.pdf |
op_rights |
https://creativecommons.org/licenses/by/4.0/ uneingeschränkt info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.5194/tc-15-5639-2021 |
container_title |
The Cryosphere |
container_volume |
15 |
container_issue |
12 |
container_start_page |
5639 |
op_container_end_page |
5658 |
_version_ |
1766093908762165248 |