Improving short-term sea ice concentration forecasts using deep learning
Reliable short-term sea ice forecasts are needed to support maritime operations in polar regions. While sea ice forecasts produced by physically based models still have limited accuracy, statistical post-processing techniques can be applied to reduce forecast errors. In this study, post-processing m...
Published in: | The Cryosphere |
---|---|
Main Authors: | , , , , , , , , |
Format: | Text |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://doi.org/10.5194/tc-18-2161-2024 https://tc.copernicus.org/articles/18/2161/2024/ |
id |
ftcopernicus:oai:publications.copernicus.org:tc115554 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:tc115554 2024-09-15T18:34:05+00:00 Improving short-term sea ice concentration forecasts using deep learning Palerme, Cyril Lavergne, Thomas Rusin, Jozef Melsom, Arne Brajard, Julien Kvanum, Are Frode Macdonald Sørensen, Atle Bertino, Laurent Müller, Malte 2024-04-30 application/pdf https://doi.org/10.5194/tc-18-2161-2024 https://tc.copernicus.org/articles/18/2161/2024/ eng eng doi:10.5194/tc-18-2161-2024 https://tc.copernicus.org/articles/18/2161/2024/ eISSN: 1994-0424 Text 2024 ftcopernicus https://doi.org/10.5194/tc-18-2161-2024 2024-08-28T05:24:15Z Reliable short-term sea ice forecasts are needed to support maritime operations in polar regions. While sea ice forecasts produced by physically based models still have limited accuracy, statistical post-processing techniques can be applied to reduce forecast errors. In this study, post-processing methods based on supervised machine learning have been developed for improving the skill of sea ice concentration forecasts from the TOPAZ4 prediction system for lead times from 1 to 10 d . The deep learning models use predictors from TOPAZ4 sea ice forecasts, weather forecasts, and sea ice concentration observations. Predicting the sea ice concentration for the next 10 d takes about 4 min (including data preparation), which is reasonable in an operational context. On average, the forecasts from the deep learning models have a root mean square error 41 % lower than TOPAZ4 forecasts and 29 % lower than forecasts based on persistence of sea ice concentration observations. They also significantly improve the forecasts for the location of the ice edges, with similar improvements as for the root mean square error. Furthermore, the impact of different types of predictors (observations, sea ice, and weather forecasts) on the predictions has been evaluated. Sea ice observations are the most important type of predictors, and the weather forecasts have a much stronger impact on the predictions than sea ice forecasts. Text Sea ice Copernicus Publications: E-Journals The Cryosphere 18 4 2161 2176 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Reliable short-term sea ice forecasts are needed to support maritime operations in polar regions. While sea ice forecasts produced by physically based models still have limited accuracy, statistical post-processing techniques can be applied to reduce forecast errors. In this study, post-processing methods based on supervised machine learning have been developed for improving the skill of sea ice concentration forecasts from the TOPAZ4 prediction system for lead times from 1 to 10 d . The deep learning models use predictors from TOPAZ4 sea ice forecasts, weather forecasts, and sea ice concentration observations. Predicting the sea ice concentration for the next 10 d takes about 4 min (including data preparation), which is reasonable in an operational context. On average, the forecasts from the deep learning models have a root mean square error 41 % lower than TOPAZ4 forecasts and 29 % lower than forecasts based on persistence of sea ice concentration observations. They also significantly improve the forecasts for the location of the ice edges, with similar improvements as for the root mean square error. Furthermore, the impact of different types of predictors (observations, sea ice, and weather forecasts) on the predictions has been evaluated. Sea ice observations are the most important type of predictors, and the weather forecasts have a much stronger impact on the predictions than sea ice forecasts. |
format |
Text |
author |
Palerme, Cyril Lavergne, Thomas Rusin, Jozef Melsom, Arne Brajard, Julien Kvanum, Are Frode Macdonald Sørensen, Atle Bertino, Laurent Müller, Malte |
spellingShingle |
Palerme, Cyril Lavergne, Thomas Rusin, Jozef Melsom, Arne Brajard, Julien Kvanum, Are Frode Macdonald Sørensen, Atle Bertino, Laurent Müller, Malte Improving short-term sea ice concentration forecasts using deep learning |
author_facet |
Palerme, Cyril Lavergne, Thomas Rusin, Jozef Melsom, Arne Brajard, Julien Kvanum, Are Frode Macdonald Sørensen, Atle Bertino, Laurent Müller, Malte |
author_sort |
Palerme, Cyril |
title |
Improving short-term sea ice concentration forecasts using deep learning |
title_short |
Improving short-term sea ice concentration forecasts using deep learning |
title_full |
Improving short-term sea ice concentration forecasts using deep learning |
title_fullStr |
Improving short-term sea ice concentration forecasts using deep learning |
title_full_unstemmed |
Improving short-term sea ice concentration forecasts using deep learning |
title_sort |
improving short-term sea ice concentration forecasts using deep learning |
publishDate |
2024 |
url |
https://doi.org/10.5194/tc-18-2161-2024 https://tc.copernicus.org/articles/18/2161/2024/ |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
eISSN: 1994-0424 |
op_relation |
doi:10.5194/tc-18-2161-2024 https://tc.copernicus.org/articles/18/2161/2024/ |
op_doi |
https://doi.org/10.5194/tc-18-2161-2024 |
container_title |
The Cryosphere |
container_volume |
18 |
container_issue |
4 |
container_start_page |
2161 |
op_container_end_page |
2176 |
_version_ |
1810475817480749056 |