Deep Learning Weather Models for Subregional Ocean Forecasting: A Case Study on the Canary Current Upwelling System

TL;DR

This study demonstrates that deep learning models, specifically graph neural networks, can significantly improve the accuracy of subregional ocean forecasts in the Canary Current upwelling system compared to traditional physical models.

Contribution

The paper adapts a graph neural network for subregional ocean prediction, showing improved accuracy over traditional models in a complex upwelling region.

Findings

Deep learning models outperform physical models in RMSE reduction.

Error reductions of up to 76% in 5-day forecasts.

Enhanced prediction of mesoscale ocean processes.

Abstract

Oceanographic forecasting impacts various sectors of society by supporting environmental conservation and economic activities. Based on global circulation models, traditional forecasting methods are computationally expensive and slow, limiting their ability to provide rapid forecasts. Recent advances in deep learning offer faster and more accurate predictions, although these data-driven models are often trained with global data from numerical simulations, which may not reflect reality. The emergence of such models presents great potential for improving ocean prediction at a subregional domain. However, their ability to predict fine-scale ocean processes, like mesoscale structures, remains largely unknown. This work aims to adapt a graph neural network initially developed for global weather forecasting to improve subregional ocean prediction, specifically focusing on the Canary Current upwelling system. The model is trained with satellite data and compared to state-of-the-art physical ocean models to assess its performance in capturing ocean dynamics. Our results show that the deep learning model surpasses traditional methods in precision despite some challenges in upwelling areas. It demonstrated superior performance in reducing RMSE errors compared to ConvLSTM and the GLORYS reanalysis, particularly in regions with complex oceanic dynamics such as Cape Ghir, Cape Bojador, and Cape Blanc. The model achieved improvements of up to 26.5% relative to ConvLSTM and error reductions of up to 76% in 5-day forecasts compared to the GLORYS reanalysis at these critical locations, highlighting its enhanced capability to capture spatial variability and improve predictive accuracy in complex areas. These findings suggest the viability of adapting meteorological data-driven models for improving subregional medium-term ocean forecasting.