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: | Text |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-15-5639-2021 https://tc.copernicus.org/articles/15/5639/2021/ |
id |
ftcopernicus:oai:publications.copernicus.org:tc93737 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tc93737 2023-05-15T14:02:17+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 Broeke, Michiel 2021-12-13 application/pdf https://doi.org/10.5194/tc-15-5639-2021 https://tc.copernicus.org/articles/15/5639/2021/ eng eng doi:10.5194/tc-15-5639-2021 https://tc.copernicus.org/articles/15/5639/2021/ eISSN: 1994-0424 Text 2021 ftcopernicus https://doi.org/10.5194/tc-15-5639-2021 2021-12-20T17:22:31Z 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. Text Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Larsen Ice Shelf Copernicus Publications: E-Journals 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 |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
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 |
Text |
author |
Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike Broeke, Michiel |
spellingShingle |
Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike Broeke, Michiel Improving surface melt estimation over the Antarctic Ice Sheet using deep learning: a proof of concept over the Larsen Ice Shelf |
author_facet |
Hu, Zhongyang Kuipers Munneke, Peter Lhermitte, Stef Izeboud, Maaike 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 |
publishDate |
2021 |
url |
https://doi.org/10.5194/tc-15-5639-2021 https://tc.copernicus.org/articles/15/5639/2021/ |
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 |
genre_facet |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Larsen Ice Shelf |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-15-5639-2021 https://tc.copernicus.org/articles/15/5639/2021/ |
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_ |
1766272477641572352 |