Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology
We introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice dynamics with deep learning techniques. Instead of parametrising single processes, a single neural network is trained to correct all model variables at the same time. This data-driven approach is applied to a regi...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/11585/958020 https://doi.org/10.5194/tc-17-2965-2023 https://tc.copernicus.org/articles/17/2965/2023/ |
id |
ftunibolognairis:oai:cris.unibo.it:11585/958020 |
---|---|
record_format |
openpolar |
spelling |
ftunibolognairis:oai:cris.unibo.it:11585/958020 2024-04-14T08:19:07+00:00 Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique 2023 ELETTRONICO https://hdl.handle.net/11585/958020 https://doi.org/10.5194/tc-17-2965-2023 https://tc.copernicus.org/articles/17/2965/2023/ eng eng info:eu-repo/semantics/altIdentifier/wos/WOS:001033899000001 volume:17 issue:7 firstpage:2965 lastpage:2991 numberofpages:27 journal:THE CRYOSPHERE https://hdl.handle.net/11585/958020 doi:10.5194/tc-17-2965-2023 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85170203408 https://tc.copernicus.org/articles/17/2965/2023/ info:eu-repo/semantics/openAccess Sea-ice Deep Learning info:eu-repo/semantics/article 2023 ftunibolognairis https://doi.org/10.5194/tc-17-2965-2023 2024-03-21T17:08:10Z We introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice dynamics with deep learning techniques. Instead of parametrising single processes, a single neural network is trained to correct all model variables at the same time. This data-driven approach is applied to a regional sea-ice model that accounts exclusively for dynamical processes with a Maxwell elasto-brittle rheology. Driven by an external wind forcing in a 40kmx200km domain, the model generates examples of sharp transitions between unfractured and fully fractured sea ice. To correct such examples, we propose a convolutional U-Net architecture which extracts features at multiple scales. We test this approach in twin experiments: the neural network learns to correct forecasts from low-resolution simulations towards high-resolution simulations for a lead time of about 10 min. At this lead time, our approach reduces the forecast errors by more than 75%, averaged over all model variables. As the most important predictors, we identify the dynamics of the model variables. Furthermore, the neural network extracts localised and directional-dependent features, which point towards the shortcomings of the low-resolution simulations. Applied to correct the forecasts every 10 min, the neural network is run together with the sea-ice model. This improves the short-term forecasts up to an hour. These results consequently show that neural networks can correct model errors from the subgrid scale for sea-ice dynamics. We therefore see this study as an important first step towards hybrid modelling to forecast sea-ice dynamics on an hourly to daily timescale. Article in Journal/Newspaper Sea ice IRIS Università degli Studi di Bologna (CRIS - Current Research Information System) The Cryosphere 17 7 2965 2991 |
institution |
Open Polar |
collection |
IRIS Università degli Studi di Bologna (CRIS - Current Research Information System) |
op_collection_id |
ftunibolognairis |
language |
English |
topic |
Sea-ice Deep Learning |
spellingShingle |
Sea-ice Deep Learning Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
topic_facet |
Sea-ice Deep Learning |
description |
We introduce a proof of concept to parametrise the unresolved subgrid scale of sea-ice dynamics with deep learning techniques. Instead of parametrising single processes, a single neural network is trained to correct all model variables at the same time. This data-driven approach is applied to a regional sea-ice model that accounts exclusively for dynamical processes with a Maxwell elasto-brittle rheology. Driven by an external wind forcing in a 40kmx200km domain, the model generates examples of sharp transitions between unfractured and fully fractured sea ice. To correct such examples, we propose a convolutional U-Net architecture which extracts features at multiple scales. We test this approach in twin experiments: the neural network learns to correct forecasts from low-resolution simulations towards high-resolution simulations for a lead time of about 10 min. At this lead time, our approach reduces the forecast errors by more than 75%, averaged over all model variables. As the most important predictors, we identify the dynamics of the model variables. Furthermore, the neural network extracts localised and directional-dependent features, which point towards the shortcomings of the low-resolution simulations. Applied to correct the forecasts every 10 min, the neural network is run together with the sea-ice model. This improves the short-term forecasts up to an hour. These results consequently show that neural networks can correct model errors from the subgrid scale for sea-ice dynamics. We therefore see this study as an important first step towards hybrid modelling to forecast sea-ice dynamics on an hourly to daily timescale. |
author2 |
Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique |
format |
Article in Journal/Newspaper |
author |
Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique |
author_facet |
Finn, Tobias Sebastian Durand, Charlotte Farchi, Alban Bocquet, Marc Chen, Yumeng Carrassi, Alberto Dansereau, Véronique |
author_sort |
Finn, Tobias Sebastian |
title |
Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
title_short |
Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
title_full |
Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
title_fullStr |
Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
title_full_unstemmed |
Deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a Maxwell elasto-brittle rheology |
title_sort |
deep learning subgrid-scale parametrisations for short-term forecasting of sea-ice dynamics with a maxwell elasto-brittle rheology |
publishDate |
2023 |
url |
https://hdl.handle.net/11585/958020 https://doi.org/10.5194/tc-17-2965-2023 https://tc.copernicus.org/articles/17/2965/2023/ |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
info:eu-repo/semantics/altIdentifier/wos/WOS:001033899000001 volume:17 issue:7 firstpage:2965 lastpage:2991 numberofpages:27 journal:THE CRYOSPHERE https://hdl.handle.net/11585/958020 doi:10.5194/tc-17-2965-2023 info:eu-repo/semantics/altIdentifier/scopus/2-s2.0-85170203408 https://tc.copernicus.org/articles/17/2965/2023/ |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.5194/tc-17-2965-2023 |
container_title |
The Cryosphere |
container_volume |
17 |
container_issue |
7 |
container_start_page |
2965 |
op_container_end_page |
2991 |
_version_ |
1796318724303618048 |