Data-driven ensemble prediction of the global ocean

TL;DR

This paper introduces FuXi-ONS, a machine-learning ensemble system for global ocean prediction that offers fast, probabilistic forecasts up to a year ahead, outperforming traditional methods in skill and efficiency.

Contribution

The paper presents the first ML-based ensemble forecasting system for the global ocean, capable of long-range probabilistic predictions with improved accuracy and computational efficiency.

Findings

FuXi-ONS improves ensemble-mean skill over baselines.

It provides competitive seasonal forecast performance.

Runs orders of magnitude faster than traditional systems.

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{\deg} 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 Ni\~no3.4 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.