Accurate Mediterranean Sea forecasting via graph-based deep learning

TL;DR

This paper introduces SeaCast, a graph-based deep learning model that significantly improves high-resolution Mediterranean Sea forecasts, outperforming traditional numerical models in accuracy and efficiency.

Contribution

We develop SeaCast, a novel graph neural network that enhances regional ocean forecasting by effectively modeling complex geometries and integrating external forcing data.

Findings

SeaCast outperforms the operational numerical model in forecast skill.

The model achieves high-resolution predictions efficiently.

Validation shows consistent improvements over existing methods.

Abstract

Accurate ocean forecasting systems are essential for understanding marine dynamics, which play a crucial role in sectors such as shipping, aquaculture, environmental monitoring, and coastal risk management. Traditional numerical solvers, while effective, are computationally expensive and time-consuming. Recent advancements in machine learning have revolutionized weather forecasting, offering fast and energy-efficient alternatives. Building on these advancements, we introduce SeaCast, a neural network designed for high-resolution regional ocean forecasting. SeaCast employs a graph-based framework to effectively handle the complex geometry of ocean grids and integrates external forcing data tailored to the regional ocean context. Our approach is validated through experiments at a high horizontal resolution using the operational numerical forecasting system of the Mediterranean Sea, along with both numerical and data-driven atmospheric forcings. Results demonstrate that SeaCast consistently outperforms the operational model in forecast skill, marking a significant advancement in regional ocean prediction.