Articles | Volume 18, issue 9
https://doi.org/10.5194/gmd-18-2665-2025
https://doi.org/10.5194/gmd-18-2665-2025
Development and technical paper
 | 
14 May 2025
Development and technical paper |  | 14 May 2025

SICNetseason V1.0: a transformer-based deep learning model for seasonal Arctic sea ice prediction by incorporating sea ice thickness data

Yibin Ren, Xiaofeng Li, and Yunhe Wang

Data sets

renyibin-iocas/SICNetseason: SICNetseason code and input/output data renyibin-iocas https://doi.org/10.5281/zenodo.14561423

Download
Short summary
This study developed a transformer-based deep learning model to predict the Arctic sea ice seasonally. By integrating the sea ice thickness data into the model, the spring prediction barrier of Arctic sea ice is optimized significantly. The model achieves better skills than the typical numerical model in predicting September’s sea ice extent seasonally. The sea ice thickness data play a key role in reducing the prediction errors of the Beaufort Sea, the East Siberian Sea and the Laptev Sea.
Share