A Mediterranean Sea Offshore Wind classification using MERRA-2 and machine learning models

This paper uses a Modern-Era Retrospective analysis for Research and Applications version 2 (MERRA-2) re-analysis to identify long-term Mediterranean Sea Offshore Wind (OW) classification possible locations. In particular, an OW based on the last 40-years period speeds highlighted best areas potential Turbine Generators (OWTG) installations in basin. Preliminary, results show that several basin zones Aegean Sea, Gulf of Lyon, Northern Morocco Tunisia regions have attractive potential. Secondly, combined forecasting model wavelet decomposition method memory neural network has been developed predict short-term wind speed considering ten years hourly data areas. The proposed prediction compared with other single models, Multilayer Perceptron (MLP) Long Short-Term Memory (LSTM), highlighting higher level accuracy. Finally, three Weibull fitting algorithms provided analyze energy • using 40 learning models. assessment mapping hot region's. A transform long network. evaluated offshore