FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution

TL;DR

FuXi-Ocean is a pioneering data-driven global ocean forecasting system that provides high-resolution, sub-daily predictions with innovative adaptive modules to improve accuracy and reduce errors over time.

Contribution

The paper introduces FuXi-Ocean, the first model to achieve six-hourly, eddy-resolving global ocean forecasts using a novel Mixture-of-Time module for adaptive, multi-temporal integration.

Findings

Outperforms existing models in temperature, salinity, and current predictions

Achieves sub-daily, high-resolution forecasts at 1/12° spatial resolution

Effectively mitigates cumulative errors in sequential ocean predictions

Abstract

Accurate, high-resolution ocean forecasting is crucial for maritime operations and environmental monitoring. While traditional numerical models are capable of producing sub-daily, eddy-resolving forecasts, they are computationally intensive and face challenges in maintaining accuracy at fine spatial and temporal scales. In contrast, recent data-driven approaches offer improved computational efficiency and emerging potential, yet typically operate at daily resolution and struggle with sub-daily predictions due to error accumulation over time. We introduce FuXi-Ocean, the first data-driven global ocean forecasting model achieving six-hourly predictions at eddy-resolving 1/12{\deg} spatial resolution, reaching depths of up to 1500 meters. The model architecture integrates a context-aware feature extraction module with a predictive network employing stacked attention blocks. The core innovation is the Mixture-of-Time (MoT) module, which adaptively integrates predictions from multiple temporal contexts by learning variable-specific reliability , mitigating cumulative errors in sequential forecasting. Through comprehensive experimental evaluation, FuXi-Ocean demonstrates superior skill in predicting key variables, including temperature, salinity, and currents, across multiple depths.