loading page

A Deep Learning Model for Improved Wind and Wave Forecasts
  • Yuval Yevnin,
  • Yaron Toledo
Yuval Yevnin
Tel Aviv University, Tel Aviv University
Author Profile
Yaron Toledo
School of Mechanical Engineering, Faculty of Engineering, Tel-Aviv University, School of Mechanical Engineering, Faculty of Engineering, Tel-Aviv University

Corresponding Author:toledo@tau.ac.il

Author Profile


The paper presents a combined numerical - deep learning (DL) approach for improving wind and wave forecasting. First, a DL model is trained to improve wind velocity forecasts by using past reanalysis data. The improved wind forecasts are used as forcing in a numerical wave forecasting model. This novel approach, used to combine physics-based and data-driven models, was tested over the Mediterranean. It resulted in ∼10% RMSE improvement in both wind velocity and wave height forecasts over operational models. This significant improvement is even more substantial at the Aegean Sea from May to September, when Etesian winds are dominant, improving wave height forecasts by over 35%. The additional computational costs of the DL model are negligible compared to the costs of either numerical models. This work has the potential to greatly improve the wind and wave forecasting models used nowadays by tailoring models to localized seasonal conditions, at negligible additional computational costs.