Abstract
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.