Work

IceCT: A MoE‐Based Model for Seasonal Arctic Sea Ice Concentration and Thickness Prediction

Year: 2026

Type: article

Abstract: The rapid decline of Arctic sea ice requires accurate prediction of its concentration (SIC) and thickness (SIT). We introduce IceCT, a deep learning model using a Mixture‐of‐Experts (MoE) framework to generate monthly SIC and SIT forecasts at a 12.5 km resolution up to 6 months ahead. Its architecture features two specialized experts—one for SIC, one for SIT—enhanced with Multi‐Head Self‐Attention (MHSA) to capture spatial patterns. A novel Spatial Gate adaptively weights the experts' contributions across the grid. Evaluations show IceCT outperforms other deep learning baselines, achieving an overall Mean Absolute Error (MAE) of 4.56% for SIC and 0.140 m for SIT, and achieves enhanced predictive skill in forecasting sea ice during the crucial summer melting period. Additionally, the model mitigates the Arctic spring predictability barrier by learning to rely more on SIT information for forecasts initialized in spring.

Source: Journal of Geophysical Research Machine Learning and Computation

DOI: 10.1029/2025jh001010

Authors: Zhewei Zhang, Yi Bao, Ning Chen, Yi Zhang, Zhou Huang

Institutions: Peking University, Nanjing University

Language: English

Topic: Arctic and Antarctic ice dynamics

Subfield: Atmospheric Science

Field: Earth and Planetary Sciences

Domain: Physical Sciences

SDG: Climate action

Open Access status: gold

Estimated APC paid: $2,500