Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks
International audience Melt rates at the base of Antarctic ice shelves are needed to drive projections of the Antarctic ice sheet mass loss. Current basal melt parameterizations struggle to link open ocean properties to ice‐shelf basal melt rates for the range of current sub‐shelf cavity geometries...
Published in: | Journal of Advances in Modeling Earth Systems |
---|---|
Main Authors: | , , , , , , , |
Other Authors: | , , , , , , , , , , , , , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2023
|
Subjects: | |
Online Access: | https://hal.sorbonne-universite.fr/hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163/document https://hal.sorbonne-universite.fr/hal-04386163/file/J%20Adv%20Model%20Earth%20Syst%20-%202023%20-%20Burgard%20-%20Emulating%20Present%20and%20Future%20Simulations%20of%20Melt%20Rates%20at%20the%20Base%20of%20Antarctic.pdf https://doi.org/10.1029/2023MS003829 |
id |
ftunivparis:oai:HAL:hal-04386163v1 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Université de Paris: Portail HAL |
op_collection_id |
ftunivparis |
language |
English |
topic |
Machine learning application to Earth system modeling [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography |
spellingShingle |
Machine learning application to Earth system modeling [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography Burgard, C. Jourdain, N, C Mathiot, P. Smith, R., S. Schäfer, R. Caillet, J. Finn, T., S. Johnson, J., E. Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
topic_facet |
Machine learning application to Earth system modeling [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography |
description |
International audience Melt rates at the base of Antarctic ice shelves are needed to drive projections of the Antarctic ice sheet mass loss. Current basal melt parameterizations struggle to link open ocean properties to ice‐shelf basal melt rates for the range of current sub‐shelf cavity geometries around Antarctica. We present a proof of concept exploring the potential of simple deep learning techniques to parameterize basal melt. We train a simple feedforward neural network, or multilayer perceptron, acting on each grid cell separately, to emulate the behavior of circum‐Antarctic cavity‐resolving ocean simulations. We find that this kind of emulator produces reasonable basal melt rates for our training ensemble, at least as close as or closer to the reference than traditional parameterizations. On an independent ensemble of simulations that was produced with the same ocean model but with different model parameters, cavity geometries and forcing, the neural network yields similar results to traditional parameterizations on present conditions. In much warmer conditions, both traditional parameterizations and neural network struggle, but the neural network tends to produce basal melt rates closer to the reference than a majority of traditional parameterizations. While this shows that such a neural network is at least as suitable for century‐scale Antarctic ice‐sheet projections as traditional parameterizations, it also highlights that tuning any parameterization on present‐like conditions can introduce biases and should be used with care. Nevertheless, this proof of concept is promising and provides a basis for further development of a deep learning basal melt parameterization. |
author2 |
Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) Processus et interactions de fine échelle océanique (PROTEO) Laboratoire d'Océanographie et du Climat : Expérimentations et Approches Numériques (LOCEAN) Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Pierre-Simon-Laplace (IPSL (FR_636)) École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Pierre-Simon-Laplace (IPSL (FR_636)) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité) NCAS-Climate Reading Department of Meteorology Reading University of Reading (UOR)-University of Reading (UOR) Physikalisch-Technische Bundesanstalt Braunschweig (PTB) Centre d'Enseignement et de Recherche en Environnement Atmosphérique (CEREA) École des Ponts ParisTech (ENPC)-EDF R&D (EDF R&D) EDF (EDF)-EDF (EDF) ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019) ANR-22-CE01-0014,AIAI,Intelligence artificielle pour améliorer le couplage de la calotte Antarctique avec le système océan/atmosphère(2022) European Project: 869304,PROTECT European Project: 820575,TiPACCs European Project: 101003536,ESM2025 |
format |
Article in Journal/Newspaper |
author |
Burgard, C. Jourdain, N, C Mathiot, P. Smith, R., S. Schäfer, R. Caillet, J. Finn, T., S. Johnson, J., E. |
author_facet |
Burgard, C. Jourdain, N, C Mathiot, P. Smith, R., S. Schäfer, R. Caillet, J. Finn, T., S. Johnson, J., E. |
author_sort |
Burgard, C. |
title |
Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
title_short |
Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
title_full |
Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
title_fullStr |
Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
title_full_unstemmed |
Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks |
title_sort |
emulating present and future simulations of melt rates at the base of antarctic ice shelves with neural networks |
publisher |
HAL CCSD |
publishDate |
2023 |
url |
https://hal.sorbonne-universite.fr/hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163/document https://hal.sorbonne-universite.fr/hal-04386163/file/J%20Adv%20Model%20Earth%20Syst%20-%202023%20-%20Burgard%20-%20Emulating%20Present%20and%20Future%20Simulations%20of%20Melt%20Rates%20at%20the%20Base%20of%20Antarctic.pdf https://doi.org/10.1029/2023MS003829 |
genre |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves |
genre_facet |
Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves |
op_source |
ISSN: 1942-2466 Journal of Advances in Modeling Earth Systems https://hal.sorbonne-universite.fr/hal-04386163 Journal of Advances in Modeling Earth Systems, 2023, 15 (12), ⟨10.1029/2023MS003829⟩ https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023MS003829 |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1029/2023MS003829 info:eu-repo/grantAgreement//869304/EU/PROjecTing sEa-level rise : from iCe sheets to local implicaTions/PROTECT info:eu-repo/grantAgreement//820575/EU/Tipping Points in Antarctic Climate Components/TiPACCs info:eu-repo/grantAgreement//101003536/EU/Earth system models for the future/ESM2025 hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163/document https://hal.sorbonne-universite.fr/hal-04386163/file/J%20Adv%20Model%20Earth%20Syst%20-%202023%20-%20Burgard%20-%20Emulating%20Present%20and%20Future%20Simulations%20of%20Melt%20Rates%20at%20the%20Base%20of%20Antarctic.pdf doi:10.1029/2023MS003829 WOS: 001129179200001 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1029/2023MS003829 |
container_title |
Journal of Advances in Modeling Earth Systems |
container_volume |
15 |
container_issue |
12 |
_version_ |
1799477296347742208 |
spelling |
ftunivparis:oai:HAL:hal-04386163v1 2024-05-19T07:29:03+00:00 Emulating Present and Future Simulations of Melt Rates at the Base of Antarctic Ice Shelves With Neural Networks Burgard, C. Jourdain, N, C Mathiot, P. Smith, R., S. Schäfer, R. Caillet, J. Finn, T., S. Johnson, J., E. Institut des Géosciences de l’Environnement (IGE) Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ) Université Grenoble Alpes (UGA) Processus et interactions de fine échelle océanique (PROTEO) Laboratoire d'Océanographie et du Climat : Expérimentations et Approches Numériques (LOCEAN) Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Pierre-Simon-Laplace (IPSL (FR_636)) École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-École normale supérieure - Paris (ENS-PSL) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)-Muséum national d'Histoire naturelle (MNHN)-Institut de Recherche pour le Développement (IRD)-Institut national des sciences de l'Univers (INSU - CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Institut Pierre-Simon-Laplace (IPSL (FR_636)) Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-École polytechnique (X)-Centre National d'Études Spatiales Toulouse (CNES)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité) NCAS-Climate Reading Department of Meteorology Reading University of Reading (UOR)-University of Reading (UOR) Physikalisch-Technische Bundesanstalt Braunschweig (PTB) Centre d'Enseignement et de Recherche en Environnement Atmosphérique (CEREA) École des Ponts ParisTech (ENPC)-EDF R&D (EDF R&D) EDF (EDF)-EDF (EDF) ANR-19-P3IA-0003,MIAI,MIAI @ Grenoble Alpes(2019) ANR-22-CE01-0014,AIAI,Intelligence artificielle pour améliorer le couplage de la calotte Antarctique avec le système océan/atmosphère(2022) European Project: 869304,PROTECT European Project: 820575,TiPACCs European Project: 101003536,ESM2025 2023-12-15 https://hal.sorbonne-universite.fr/hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163/document https://hal.sorbonne-universite.fr/hal-04386163/file/J%20Adv%20Model%20Earth%20Syst%20-%202023%20-%20Burgard%20-%20Emulating%20Present%20and%20Future%20Simulations%20of%20Melt%20Rates%20at%20the%20Base%20of%20Antarctic.pdf https://doi.org/10.1029/2023MS003829 en eng HAL CCSD American Geophysical Union info:eu-repo/semantics/altIdentifier/doi/10.1029/2023MS003829 info:eu-repo/grantAgreement//869304/EU/PROjecTing sEa-level rise : from iCe sheets to local implicaTions/PROTECT info:eu-repo/grantAgreement//820575/EU/Tipping Points in Antarctic Climate Components/TiPACCs info:eu-repo/grantAgreement//101003536/EU/Earth system models for the future/ESM2025 hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163 https://hal.sorbonne-universite.fr/hal-04386163/document https://hal.sorbonne-universite.fr/hal-04386163/file/J%20Adv%20Model%20Earth%20Syst%20-%202023%20-%20Burgard%20-%20Emulating%20Present%20and%20Future%20Simulations%20of%20Melt%20Rates%20at%20the%20Base%20of%20Antarctic.pdf doi:10.1029/2023MS003829 WOS: 001129179200001 info:eu-repo/semantics/OpenAccess ISSN: 1942-2466 Journal of Advances in Modeling Earth Systems https://hal.sorbonne-universite.fr/hal-04386163 Journal of Advances in Modeling Earth Systems, 2023, 15 (12), ⟨10.1029/2023MS003829⟩ https://agupubs.onlinelibrary.wiley.com/doi/10.1029/2023MS003829 Machine learning application to Earth system modeling [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology [SDU.STU.OC]Sciences of the Universe [physics]/Earth Sciences/Oceanography info:eu-repo/semantics/article Journal articles 2023 ftunivparis https://doi.org/10.1029/2023MS003829 2024-04-23T03:29:35Z International audience Melt rates at the base of Antarctic ice shelves are needed to drive projections of the Antarctic ice sheet mass loss. Current basal melt parameterizations struggle to link open ocean properties to ice‐shelf basal melt rates for the range of current sub‐shelf cavity geometries around Antarctica. We present a proof of concept exploring the potential of simple deep learning techniques to parameterize basal melt. We train a simple feedforward neural network, or multilayer perceptron, acting on each grid cell separately, to emulate the behavior of circum‐Antarctic cavity‐resolving ocean simulations. We find that this kind of emulator produces reasonable basal melt rates for our training ensemble, at least as close as or closer to the reference than traditional parameterizations. On an independent ensemble of simulations that was produced with the same ocean model but with different model parameters, cavity geometries and forcing, the neural network yields similar results to traditional parameterizations on present conditions. In much warmer conditions, both traditional parameterizations and neural network struggle, but the neural network tends to produce basal melt rates closer to the reference than a majority of traditional parameterizations. While this shows that such a neural network is at least as suitable for century‐scale Antarctic ice‐sheet projections as traditional parameterizations, it also highlights that tuning any parameterization on present‐like conditions can introduce biases and should be used with care. Nevertheless, this proof of concept is promising and provides a basis for further development of a deep learning basal melt parameterization. Article in Journal/Newspaper Antarc* Antarctic Antarctica Ice Sheet Ice Shelf Ice Shelves Université de Paris: Portail HAL Journal of Advances in Modeling Earth Systems 15 12 |