MedFormer: a data-driven model for forecasting the Mediterranean Sea

Abstract Accurate ocean forecasting is essential for supporting a wide range of marine applications. Recent advances in artificial intelligence have highlighted the potential of data-driven models to outperform traditional numerical approaches, particularly in atmospheric weather forecasting. However, extending these methods to ocean systems remains challenging due to their inherently slower dynamics and complex boundary conditions. In this work, we present MedFormer, a fully data-driven deep learning model specifically designed for medium-range ocean forecasting in the Mediterranean Sea. MedFormer is based on a U-Net architecture augmented with 3D attention mechanism, operating at a high horizontal resolution of 1/24°. The model is trained on 20 years of daily ocean reanalysis data and fine-tuned with high-resolution operational analyses. It generates 9-day forecasts using an autoregressive strategy. The model leverages both historical ocean states and atmospheric forcings, making it well-suited for operational use. We benchmark MedFormer against the state-of-the-art Mediterranean Forecasting System (MedFS), developed at the Euro-Mediterranean Center on Climate Change (CMCC), using both analysis data and independent observations. The forecast skills, evaluated with the Root Mean Squared Difference and the Anomaly Correlation Coefficient, indicate that MedFormer demonstrates improved forecast skill over MedFS across key 3D ocean variables, with the most pronounced gains during summer and autumn. These findings underscore the potential of data-driven approaches like MedFormer to complement traditional numerical ocean forecasting systems, demonstrating competitive or improved accuracy for most evaluated variables, with the exception of Sea Surface Height alongside substantial gains in computational efficiency.