Advancing global sea ice prediction capabilities using a fully-coupled climate model with integrated machine learning

TL;DR

This paper presents a hybrid climate modeling framework embedding machine learning for online sea ice bias correction, significantly improving forecast accuracy in the Arctic and Antarctic by exposing ML models to coupled feedbacks.

Contribution

It introduces a fully-coupled climate model with integrated ML that enhances sea ice prediction accuracy and demonstrates the importance of feedback exposure for model generalization.

Findings

Hybrid_CPL reduces Arctic and Antarctic forecast errors

ML models require feedback exposure for effective generalization

Significant error reduction in 4-6 month Antarctic forecasts

Abstract

We showcase a hybrid modeling framework which embeds machine learning (ML) inference into the GFDL SPEAR climate model, for online sea ice bias correction during a set of global fully-coupled 1-year retrospective forecasts. We compare two hybrid versions of SPEAR to understand the importance of exposing ML models to coupled ice-atmosphere-ocean feedbacks before implementation into fully-coupled simulations: Hybrid_CPL (with feedbacks) and Hybrid_IO (without feedbacks). Relative to SPEAR, Hybrid_CPL systematically reduces seasonal forecast errors in the Arctic and significantly reduces Antarctic errors for target months May-December, with >2x error reduction in 4-6-month lead forecasts of Antarctic winter sea ice extent. Meanwhile, Hybrid_IO suffers from out-of-sample behavior which can trigger a chain of Southern Ocean feedbacks, leading to ice-free Antarctic summers. Our results demonstrate that ML can significantly improve numerical sea ice prediction capabilities and that exposing ML models to coupled ice-atmosphere-ocean processes is essential for generalization in fully-coupled simulations.