SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data

<p>The Arctic sea ice suffers dramatic retreat in summer and fall, which has far-reaching consequences for the global climate and commercial activities. Accurate seasonal sea ice predictions significantly infer climate change and are crucial for planning commercial activities. However, seasona...

Full description

Saved in:
Bibliographic Details
Main Authors: Y. Ren, X. Li, Y. Wang
Format: Article
Language:English
Published: Copernicus Publications 2025-05-01
Series:Geoscientific Model Development
Online Access:https://gmd.copernicus.org/articles/18/2665/2025/gmd-18-2665-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850278921318170624
author Y. Ren
Y. Ren
Y. Ren
X. Li
X. Li
X. Li
Y. Wang
Y. Wang
Y. Wang
author_facet Y. Ren
Y. Ren
Y. Ren
X. Li
X. Li
X. Li
Y. Wang
Y. Wang
Y. Wang
author_sort Y. Ren
collection DOAJ
description <p>The Arctic sea ice suffers dramatic retreat in summer and fall, which has far-reaching consequences for the global climate and commercial activities. Accurate seasonal sea ice predictions significantly infer climate change and are crucial for planning commercial activities. However, seasonal prediction of the summer sea ice encounters a significant obstacle known as the spring predictability barrier (SPB): predictions made later than the date of melt onset (roughly May) demonstrate good skill in predicting summer sea ice, while predictions made during or earlier than May exhibit considerably lower skill. This study develops a transformer-based deep learning model, SICNet<span class="inline-formula"><sub>season</sub></span> (V1.0), to predict the Arctic sea ice concentration on a seasonal scale. Including spring sea ice thickness (SIT) data in the model significantly improves the prediction skill at the SPB point. A 20-year (2000–2019) test demonstrates that the detrended anomaly correlation coefficient (ACC) of September sea ice extent (sea ice concentration <span class="inline-formula">&gt;15</span> %) predicted by our model during May and April is improved by 7.7 % and 10.61 %, respectively, compared to the ACC predicted by the state-of-the-art dynamic model SEAS5 from the European Centre for Medium-Range Weather Forecasts (ECMWF). Compared with the anomaly persistence benchmark, the mentioned improvement is 41.02 % and 36.33 %. Our deep learning model significantly reduces prediction errors in terms of September's sea ice concentration on seasonal scales compared to SEAS5 and the anomaly persistence model (Persistence). The spring SIT data are key in optimizing the predictions around the SPB, contributing to an enhancement in ACC of more than 20 % in September's sea ice extent (SIE) for 4- to 5-month-lead predictions. Our model achieves good generalizability in predicting the September SIE of 2020–2023.</p>
format Article
id doaj-art-578bc51e007446b6a3089872f072f3f9
institution OA Journals
issn 1991-959X
1991-9603
language English
publishDate 2025-05-01
publisher Copernicus Publications
record_format Article
series Geoscientific Model Development
spelling doaj-art-578bc51e007446b6a3089872f072f3f92025-08-20T01:49:16ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032025-05-01182665267810.5194/gmd-18-2665-2025SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness dataY. Ren0Y. Ren1Y. Ren2X. Li3X. Li4X. Li5Y. Wang6Y. Wang7Y. Wang8Key Laboratory of Ocean Observation and Forecasting, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaKey Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaQingdao Key Laboratory of Artificial Intelligence Oceanography, Qingdao, ChinaKey Laboratory of Ocean Observation and Forecasting, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaKey Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaQingdao Key Laboratory of Artificial Intelligence Oceanography, Qingdao, ChinaKey Laboratory of Ocean Observation and Forecasting, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaKey Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao, ChinaQingdao Key Laboratory of Artificial Intelligence Oceanography, Qingdao, China<p>The Arctic sea ice suffers dramatic retreat in summer and fall, which has far-reaching consequences for the global climate and commercial activities. Accurate seasonal sea ice predictions significantly infer climate change and are crucial for planning commercial activities. However, seasonal prediction of the summer sea ice encounters a significant obstacle known as the spring predictability barrier (SPB): predictions made later than the date of melt onset (roughly May) demonstrate good skill in predicting summer sea ice, while predictions made during or earlier than May exhibit considerably lower skill. This study develops a transformer-based deep learning model, SICNet<span class="inline-formula"><sub>season</sub></span> (V1.0), to predict the Arctic sea ice concentration on a seasonal scale. Including spring sea ice thickness (SIT) data in the model significantly improves the prediction skill at the SPB point. A 20-year (2000–2019) test demonstrates that the detrended anomaly correlation coefficient (ACC) of September sea ice extent (sea ice concentration <span class="inline-formula">&gt;15</span> %) predicted by our model during May and April is improved by 7.7 % and 10.61 %, respectively, compared to the ACC predicted by the state-of-the-art dynamic model SEAS5 from the European Centre for Medium-Range Weather Forecasts (ECMWF). Compared with the anomaly persistence benchmark, the mentioned improvement is 41.02 % and 36.33 %. Our deep learning model significantly reduces prediction errors in terms of September's sea ice concentration on seasonal scales compared to SEAS5 and the anomaly persistence model (Persistence). The spring SIT data are key in optimizing the predictions around the SPB, contributing to an enhancement in ACC of more than 20 % in September's sea ice extent (SIE) for 4- to 5-month-lead predictions. Our model achieves good generalizability in predicting the September SIE of 2020–2023.</p>https://gmd.copernicus.org/articles/18/2665/2025/gmd-18-2665-2025.pdf
spellingShingle Y. Ren
Y. Ren
Y. Ren
X. Li
X. Li
X. Li
Y. Wang
Y. Wang
Y. Wang
SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
Geoscientific Model Development
title SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
title_full SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
title_fullStr SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
title_full_unstemmed SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
title_short SICNet<sub>season</sub> V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data
title_sort sicnet sub season sub v1 0 a transformer based deep learning model for seasonal arctic sea ice prediction by incorporating sea ice thickness data
url https://gmd.copernicus.org/articles/18/2665/2025/gmd-18-2665-2025.pdf
work_keys_str_mv AT yren sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT yren sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT yren sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT xli sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT xli sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT xli sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT ywang sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT ywang sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata
AT ywang sicnetsubseasonsubv10atransformerbaseddeeplearningmodelforseasonalarcticseaicepredictionbyincorporatingseaicethicknessdata