Data-driven ensemble prediction of the global ocean

2026-03-19

AI Summary

This work proposes FuXi-ONS, the first machine learning–based global ocean ensemble forecasting system designed to address the challenge of efficient and accurate long-range (5–365 days) probabilistic prediction of multiple oceanic variables. Innovatively integrating a physics-informed structured perturbation generation mechanism with an atmospheric encoding module, FuXi-ONS combines deep learning with physical constraints and is trained on GLORYS12 reanalysis data to rapidly produce ensemble forecasts of sea surface temperature, sea surface height, subsurface temperature and salinity, and ocean currents. Compared to conventional deterministic and noise-perturbed baselines, FuXi-ONS demonstrates substantially improved ensemble mean skill and probabilistic reliability. Its seasonal prediction performance for sea surface temperature and the Niño3.4 index rivals that of state-of-the-art numerical models while achieving computational efficiency gains of several orders of magnitude.

Technology Category

• Machine Learning: Ensemble Methods
• Natural Language Processing: Learning & Optimization for NLP
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Data-driven models have advanced deterministic ocean forecasting, but extending machine learning to probabilistic global ocean prediction remains an open challenge. Here we introduce FuXi-ONS, the first machine-learning ensemble forecasting system for the global ocean, providing 5-day forecasts on a global 1° grid up to 365 days for sea-surface temperature, sea-surface height, subsurface temperature, salinity and ocean currents. Rather than relying on repeated integration of computationally expensive numerical models, FuXi-ONS learns physically structured perturbations and incorporates an atmospheric encoding module to stabilize long-range forecasts. Evaluated against GLORYS12 reanalysis, FuXi-ONS improves both ensemble-mean skill and probabilistic forecast quality relative to deterministic and noise-perturbed baselines, and shows competitive performance against established seasonal forecast references for SST and Niño3.4 variability, while running orders of magnitude faster than conventional ensemble systems. These results provide a strong example of machine learning advancing a core problem in ocean science, and establish a practical path toward efficient probabilistic ocean forecasting and climate risk assessment.

Problem

• probabilistic forecasting
• ensemble prediction
• global ocean
• machine learning
• ocean forecasting

Innovation

• machine learning
• ensemble forecasting
• probabilistic prediction
• ocean modeling
• atmospheric encoding