Surrogate wave modelling to improve operational wave data for offshore wind farms

Abstract

The continued expansion of offshore wind as a global energy technology represents a significant expansion of infrastructure into a range of coastal and oceanic regions. Effective design, operation and understanding physical impacts of turbines benefit from a detailed understanding of the wave conditions. In order to cover the spatial extent of offshore wind farms and to ensure high quality data, some combination of in-situ measurements and phase averaging wave modelling are commonly applied. These are used for monitoring current conditions and for short term forecasts that govern crucial operational decisions. Inaccuracies in this process lead to vessels missing suitable conditions to carry out an operation, or operations being aborted due to unsafe conditions. Both of these outcomes, cost money or affect safety.This work reviews recent progress in using machine learning to develop surrogate wave modelling that can offer real-time spatial wave data leveraging a combination of in-situ measurements and model hindcasts, but without relying on continuous processing from traditional wave models. The outcomes show an improvement in accuracy of real-time wave predictions when compared to regional wave modelling, available at a fraction of the computational cost. This highlights the potential of this approach to change how wave data is provided for operational purposes, with immediate potential for reduced costs and improved safety for vessels working at offshore wind farms. The results also highlight the ongoing potential for research and development of surrogate models as part of the future of numerical wave modelling.