HybridOM: Hybrid Physics-Based and Data-Driven Global Ocean Modeling with Efficient Spatial Downscaling

TL;DR

HybridOM combines physics-based numerical solvers with neural networks to create an efficient, accurate, and physically consistent global ocean model suitable for climate science and operational forecasting.

Contribution

It introduces a novel hybrid framework integrating differentiable physics-based solvers with neural networks and a regional downscaling mechanism for efficient high-resolution ocean modeling.

Findings

Achieves state-of-the-art accuracy in ocean simulation tasks.

Maintains physical consistency and robustness over long-term simulations.

Demonstrates efficiency comparable to AI-based methods.

Abstract

Global ocean modeling is vital for climate science but struggles to balance computational efficiency with accuracy. Traditional numerical solvers are accurate but computationally expensive, while pure deep learning approaches, though fast, often lack physical consistency and long-term stability. To address this, we introduce HybridOM, a framework integrating a lightweight, differentiable numerical solver as a skeleton to enforce physical laws, with a neural network as the flesh to correct subgrid-scale dynamics. To enable efficient high-resolution modeling, we further introduce a physics-informed regional downscaling mechanism based on flux gating. This design achieves the inference efficiency of AI-based methods while preserving the accuracy and robustness of physical models. Extensive experiments on the GLORYS12V1 and OceanBench dataset validate HybridOM's performance in two distinct regimes: long-term subseasonal-to-seasonal simulation and short-term operational forecasting coupled with the FuXi-2.0 weather model. Results demonstrate that HybridOM achieves state-of-the-art accuracy while strictly maintaining physical consistency, offering a robust solution for next-generation ocean digital twins. Our source code is available at https://github.com/ChiyodaMomo01/HybridOM.