Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach
Arctic sea ice thickness (SIT) remains one of the most crucial yet challenging parameters to estimate. Satellite data generally presents temporal and spatial discontinuities, which constrain studies focusing on long-term evolution. Since 2011, the combined satellite product CS2SMOS enables more accu...
Main Authors: | , , , , |
---|---|
Format: | Text |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5194/egusphere-2024-1896 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-1896/ |
id |
ftcopernicus:oai:publications.copernicus.org:egusphere121282 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:egusphere121282 2024-09-15T18:35:12+00:00 Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach Edel, Léo Xie, Jiping Korosov, Anton Brajard, Julien Bertino, Laurent 2024-07-03 application/pdf https://doi.org/10.5194/egusphere-2024-1896 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-1896/ eng eng doi:10.5194/egusphere-2024-1896 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-1896/ eISSN: Text 2024 ftcopernicus https://doi.org/10.5194/egusphere-2024-1896 2024-08-28T05:24:22Z Arctic sea ice thickness (SIT) remains one of the most crucial yet challenging parameters to estimate. Satellite data generally presents temporal and spatial discontinuities, which constrain studies focusing on long-term evolution. Since 2011, the combined satellite product CS2SMOS enables more accurate SIT retrievals that significantly decrease modelled SIT errors during assimilation. Can we extrapolate the benefits of data assimilation to past periods lacking accurate SIT observations? In this study, we train a machine learning (ML) algorithm to learn the systematic SIT errors between two versions of the model TOPAZ4 over 2011–2022, with and without CS2SMOS assimilation, to predict the SIT error and extrapolate the SIT prior to 2011. The ML algorithm relies on SIT coming from the two versions of TOPAZ4, various oceanographic variables, and atmospheric forcings from ERA5. Over the test period 2011–2013, the ML method outperforms TOPAZ4 without CS2SMOS assimilation when compared to TOPAZ4 assimilating CS2SMOS. The root mean square error of Arctic averaged SIT decreases from 0.42 to 0.28 meters and the bias from -0.18 to 0.01 meters. Also, despite the lack of observations available for assimilation in summer, our method still demonstrates a crucial improvement in SIT. Relative to independent mooring data in the Central Arctic between 2001 and 2010, mean SIT bias reduces from -1.74 meters to -0.85 meters when using the ML algorithm. Ultimately, the ML-adjusted SIT reconstruction reveals an Arctic mean SIT of 1.61 meters in 1992 compared to 1.08 meters in 2022. This corresponds to a decline in total sea ice volume from 19,690 to 12,700 km 3 , with an associated trend of -3,153 km 3 /decade. These changes are accompanied by a distinct shift in SIT distribution. Our innovative approach proves its ability to correct a significant part of the primary biases of the model by combining data assimilation with machine learning. Although this new reconstructed SIT dataset has not yet been assimilated into ... Text Sea ice Copernicus Publications: E-Journals |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Arctic sea ice thickness (SIT) remains one of the most crucial yet challenging parameters to estimate. Satellite data generally presents temporal and spatial discontinuities, which constrain studies focusing on long-term evolution. Since 2011, the combined satellite product CS2SMOS enables more accurate SIT retrievals that significantly decrease modelled SIT errors during assimilation. Can we extrapolate the benefits of data assimilation to past periods lacking accurate SIT observations? In this study, we train a machine learning (ML) algorithm to learn the systematic SIT errors between two versions of the model TOPAZ4 over 2011–2022, with and without CS2SMOS assimilation, to predict the SIT error and extrapolate the SIT prior to 2011. The ML algorithm relies on SIT coming from the two versions of TOPAZ4, various oceanographic variables, and atmospheric forcings from ERA5. Over the test period 2011–2013, the ML method outperforms TOPAZ4 without CS2SMOS assimilation when compared to TOPAZ4 assimilating CS2SMOS. The root mean square error of Arctic averaged SIT decreases from 0.42 to 0.28 meters and the bias from -0.18 to 0.01 meters. Also, despite the lack of observations available for assimilation in summer, our method still demonstrates a crucial improvement in SIT. Relative to independent mooring data in the Central Arctic between 2001 and 2010, mean SIT bias reduces from -1.74 meters to -0.85 meters when using the ML algorithm. Ultimately, the ML-adjusted SIT reconstruction reveals an Arctic mean SIT of 1.61 meters in 1992 compared to 1.08 meters in 2022. This corresponds to a decline in total sea ice volume from 19,690 to 12,700 km 3 , with an associated trend of -3,153 km 3 /decade. These changes are accompanied by a distinct shift in SIT distribution. Our innovative approach proves its ability to correct a significant part of the primary biases of the model by combining data assimilation with machine learning. Although this new reconstructed SIT dataset has not yet been assimilated into ... |
format |
Text |
author |
Edel, Léo Xie, Jiping Korosov, Anton Brajard, Julien Bertino, Laurent |
spellingShingle |
Edel, Léo Xie, Jiping Korosov, Anton Brajard, Julien Bertino, Laurent Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
author_facet |
Edel, Léo Xie, Jiping Korosov, Anton Brajard, Julien Bertino, Laurent |
author_sort |
Edel, Léo |
title |
Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
title_short |
Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
title_full |
Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
title_fullStr |
Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
title_full_unstemmed |
Reconstruction of Arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
title_sort |
reconstruction of arctic sea ice thickness (1992–2010) based on a hybrid machine learning and data assimilation approach |
publishDate |
2024 |
url |
https://doi.org/10.5194/egusphere-2024-1896 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-1896/ |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
eISSN: |
op_relation |
doi:10.5194/egusphere-2024-1896 https://egusphere.copernicus.org/preprints/2024/egusphere-2024-1896/ |
op_doi |
https://doi.org/10.5194/egusphere-2024-1896 |
_version_ |
1810478151813300224 |