Resumen
One of the most promising solutions that stands out to mitigate climate change is floating offshore wind turbines (FOWTs). Although they are very efficient in producing clean energy, the harsh environmental conditions they are subjected to, mainly strong winds and waves, produce structural fatigue and may cause them to lose efficiency. Thus, it is imperative to develop models to facilitate their deployment while maximizing energy production and ensuring the structure?s safety. This work applies machine learning (ML) techniques to obtain predictive models of the most relevant metocean variables involved. Specifically, wind speed, significant wave height, and the misalignment between wind and waves have been analyzed, pre-processed and modeled based on actual data. Linear regression (LR), support vector machines regression (SVR), Gaussian process regression (GPR) and neural network (NN)-based solutions have been applied and compared. The results show that Nonlinear autoregressive with an exogenous input neural network (NARX) is the best algorithm for both wind speed and misalignment forecasting in the time domain (72% accuracy) and GPR for wave height (90.85% accuracy). In conclusion, these models are vital to deploying and installing FOWTs and making them profitable.