Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning
International audience Reliable boundary-layer turbulence parametrizations for polar conditions are needed to reduce uncertainty in projections of Arctic sea ice melting rate and its potential global repercussions. Surface turbulent fluxes of sensible and latent heat are typically represented in wea...
Published in: | Geophysical Research Letters |
---|---|
Main Authors: | , , , , |
Other Authors: | , , , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
HAL CCSD
2023
|
Subjects: | |
Online Access: | https://hal.science/hal-04554644 https://hal.science/hal-04554644/document https://hal.science/hal-04554644/file/Cummins_et_al_2023.pdf https://doi.org/10.1029/2023gl105698 |
id |
ftutoulouse3hal:oai:HAL:hal-04554644v1 |
---|---|
record_format |
openpolar |
spelling |
ftutoulouse3hal:oai:HAL:hal-04554644v1 2024-05-19T07:35:38+00:00 Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning Cummins, Donald, P Guemas, Virginie Cox, Christopher, J Gallagher, Michael, R Shupe, Matthew, D Cooperative Institute for Research in Environmental Sciences (CIRES) University of Colorado Boulder -National Oceanic and Atmospheric Administration (NOAA) National Oceanic and Atmospheric Administration (NOAA) NOAA Physical Sciences Laboratory (PSL) Centre national de recherches météorologiques (CNRM) Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP) Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3) Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3) Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS) ANR-17-MPGA-0003,ASET,Atmosphere - Sea ice Exchanges and Teleconections(2017) European Project: 101003826,CRiceS 2023-12-06 https://hal.science/hal-04554644 https://hal.science/hal-04554644/document https://hal.science/hal-04554644/file/Cummins_et_al_2023.pdf https://doi.org/10.1029/2023gl105698 en eng HAL CCSD American Geophysical Union info:eu-repo/semantics/altIdentifier/doi/10.1029/2023gl105698 info:eu-repo/grantAgreement//101003826/EU/Climate Relevant interactions and feedbacks: the key role of sea ice and Snow in the polar and global climate system/CRiceS hal-04554644 https://hal.science/hal-04554644 https://hal.science/hal-04554644/document https://hal.science/hal-04554644/file/Cummins_et_al_2023.pdf doi:10.1029/2023gl105698 info:eu-repo/semantics/OpenAccess ISSN: 0094-8276 EISSN: 1944-8007 Geophysical Research Letters https://hal.science/hal-04554644 Geophysical Research Letters, 2023, 50, ⟨10.1029/2023gl105698⟩ [SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology info:eu-repo/semantics/article Journal articles 2023 ftutoulouse3hal https://doi.org/10.1029/2023gl105698 2024-04-25T00:47:36Z International audience Reliable boundary-layer turbulence parametrizations for polar conditions are needed to reduce uncertainty in projections of Arctic sea ice melting rate and its potential global repercussions. Surface turbulent fluxes of sensible and latent heat are typically represented in weather/climate models using bulk formulae based on the Monin-Obukhov Similarity Theory, sometimes finely tuned to high stability conditions and the potential presence of sea ice. In this study, we test the performance of new, machine-learning (ML) flux parametrizations, using an advanced polar-specific bulk algorithm as a baseline. Neural networks, trained on observations from previous Arctic campaigns, are used to predict surface turbulent fluxes measured over sea ice as part of the recent MOSAiC expedition. The ML parametrizations outperform the bulk at the MOSAiC sites, with RMSE reductions of up to 70 percent. We provide a plug-in Fortran implementation of the neural networks for use in models. Article in Journal/Newspaper Arctic Sea ice Université Toulouse III - Paul Sabatier: HAL-UPS Geophysical Research Letters 50 23 |
institution |
Open Polar |
collection |
Université Toulouse III - Paul Sabatier: HAL-UPS |
op_collection_id |
ftutoulouse3hal |
language |
English |
topic |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology |
spellingShingle |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology Cummins, Donald, P Guemas, Virginie Cox, Christopher, J Gallagher, Michael, R Shupe, Matthew, D Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
topic_facet |
[SDU.STU.GP]Sciences of the Universe [physics]/Earth Sciences/Geophysics [physics.geo-ph] [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation [SDU.STU.CL]Sciences of the Universe [physics]/Earth Sciences/Climatology [SDU.STU.GL]Sciences of the Universe [physics]/Earth Sciences/Glaciology |
description |
International audience Reliable boundary-layer turbulence parametrizations for polar conditions are needed to reduce uncertainty in projections of Arctic sea ice melting rate and its potential global repercussions. Surface turbulent fluxes of sensible and latent heat are typically represented in weather/climate models using bulk formulae based on the Monin-Obukhov Similarity Theory, sometimes finely tuned to high stability conditions and the potential presence of sea ice. In this study, we test the performance of new, machine-learning (ML) flux parametrizations, using an advanced polar-specific bulk algorithm as a baseline. Neural networks, trained on observations from previous Arctic campaigns, are used to predict surface turbulent fluxes measured over sea ice as part of the recent MOSAiC expedition. The ML parametrizations outperform the bulk at the MOSAiC sites, with RMSE reductions of up to 70 percent. We provide a plug-in Fortran implementation of the neural networks for use in models. |
author2 |
Cooperative Institute for Research in Environmental Sciences (CIRES) University of Colorado Boulder -National Oceanic and Atmospheric Administration (NOAA) National Oceanic and Atmospheric Administration (NOAA) NOAA Physical Sciences Laboratory (PSL) Centre national de recherches météorologiques (CNRM) Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP) Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3) Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3) Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS) ANR-17-MPGA-0003,ASET,Atmosphere - Sea ice Exchanges and Teleconections(2017) European Project: 101003826,CRiceS |
format |
Article in Journal/Newspaper |
author |
Cummins, Donald, P Guemas, Virginie Cox, Christopher, J Gallagher, Michael, R Shupe, Matthew, D |
author_facet |
Cummins, Donald, P Guemas, Virginie Cox, Christopher, J Gallagher, Michael, R Shupe, Matthew, D |
author_sort |
Cummins, Donald, P |
title |
Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
title_short |
Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
title_full |
Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
title_fullStr |
Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
title_full_unstemmed |
Surface Turbulent Fluxes From the MOSAiC Campaign Predicted by Machine Learning |
title_sort |
surface turbulent fluxes from the mosaic campaign predicted by machine learning |
publisher |
HAL CCSD |
publishDate |
2023 |
url |
https://hal.science/hal-04554644 https://hal.science/hal-04554644/document https://hal.science/hal-04554644/file/Cummins_et_al_2023.pdf https://doi.org/10.1029/2023gl105698 |
genre |
Arctic Sea ice |
genre_facet |
Arctic Sea ice |
op_source |
ISSN: 0094-8276 EISSN: 1944-8007 Geophysical Research Letters https://hal.science/hal-04554644 Geophysical Research Letters, 2023, 50, ⟨10.1029/2023gl105698⟩ |
op_relation |
info:eu-repo/semantics/altIdentifier/doi/10.1029/2023gl105698 info:eu-repo/grantAgreement//101003826/EU/Climate Relevant interactions and feedbacks: the key role of sea ice and Snow in the polar and global climate system/CRiceS hal-04554644 https://hal.science/hal-04554644 https://hal.science/hal-04554644/document https://hal.science/hal-04554644/file/Cummins_et_al_2023.pdf doi:10.1029/2023gl105698 |
op_rights |
info:eu-repo/semantics/OpenAccess |
op_doi |
https://doi.org/10.1029/2023gl105698 |
container_title |
Geophysical Research Letters |
container_volume |
50 |
container_issue |
23 |
_version_ |
1799474441119334400 |