Learning-Based Methods and the Future of Numerical Ocean and Sea Ice Modeling

The field of operational oceanography is undergoing a significant evolu- tion with the increasing integration of artificial intelligence (AI) meth- ods, which are complementing and, in some cases, redefining tradi- tional numerical modeling approaches. This review explores how AI methods—particularly model-based autoregressive emulators, hybrid modeling, and end-to-end model-free approaches—are reshaping the representation of ocean and sea-ice dynamics in operational systems. We focus on three key objects: sea-ice parameters, near-surface ocean properties, and the 3D ocean state, each characterized by distinct ob- servational and dynamical challenges. While AI-driven innovations of- fer new opportunities for improved monitoring, forecasting, and uncer- tainty quantification, their long-term impact on operational systems remains uncertain, especially given the sparsity of subsurface observa- tions and the complexity of ocean dynamics. By synthesizing recent advances and identifying open questions, this paper aims to guide the ocean modeling community toward a future where AI and physics-based approaches coexist synergistically.