No abstract

<p>Machine learning is increasingly being applied to ocean wave modelling. Surrogate modelling has the potential to reduce or bypass the large computational requirements, creating a low computational-cost model that offers a high level of accuracy. One approach integrates in-situ measurements and historical model runs to achieve the spatial coverage of the model and the accuracy of the in-situ measurements. Once operational, such a system requires very little computational power, meaning that it could be deployed to a mobile phone, operational vessel, or autonomous vessel to give continuous data. As such, it makes a significant change to the availability of met-ocean data with potential to revolutionise data provision and use in marine and coastal settings.</p><p>This presentation explores the impact that an underlying physics-based model can have in such a machine learning driven framework; comparing training the system on a bespoke regional SWAN wave model developed for wave energy developments in the South West of the UK against training using the larger North-West European Shelf long term hindcast wave model run by the UK Met Office. The presentation discusses the differences in the underlying NWP models, and the impacts that these have on the surrogate wave models’ accuracy in both nowcasting and forecasting wave conditions at areas of interest for renewable energy developments. The results identify the importance in having a high quality, validated, NWP model for training such a system and the way in which the machine learning methods can propagate and exaggerate the underlying model uncertainties.</p>

<p>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.</p><p>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.</p>