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

2025-06-03

AI Summary

To address the high computational cost of traditional numerical models and the low accuracy and severe error accumulation in data-driven approaches for high spatiotemporal-resolution sub-daily ocean forecasting, this study develops the first global, data-driven ocean forecasting system with 6-hourly temporal resolution, 1/12° horizontal resolution, and vertical coverage down to 1500 m. We propose a Mixture-of-Timescales (MoT) module that adaptively fuses multi-scale temporal information and learns variable-specific reliability weights to effectively suppress error propagation. Coupled with context-aware feature extraction and a stacked attention network, the framework enables end-to-end, high-resolution spatiotemporal modeling. Comprehensive evaluation across multiple variables—including temperature, salinity, and three-dimensional currents—and numerous depth levels demonstrates consistent and significant improvements over state-of-the-art numerical and data-driven methods, with markedly enhanced forecast skill.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

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.

Problem

• High-resolution sub-daily ocean forecasting challenges traditional models
• Data-driven models struggle with error accumulation in sub-daily predictions
• FuXi-Ocean enables accurate 6-hourly global forecasts at 1/12° resolution

Innovation

• Data-driven global ocean forecasting model
• Mixture-of-Time module for error mitigation
• Six-hourly predictions at 1/12° resolution