A novel model for the study of future maritime climate using artificial neural networks and Monte Carlo simulations under the context of climate change.

• ANNs and Monte Carlo simulations are used to obtain future shallow water climate. • Monte Carlo simulations and statistics aid regional climate change projections. • ANNs exploit the data generated by Monte Carlo simulations. • An adaptation of the equation for Tp is necessary to reflect new climate conditions. • Up to 1.6 m increase in extreme Hs are expected in Western Mediterranean by 2050. This paper proposes a new model to study future coastal maritime climate under climate change context. This new model combines statistical analysis, Monte Carlo simulations and Artificial Neural Networks (ANNs). Statistical analysis and Monte Carlo simulations are used to extrapolate future wave climate under climate change context at a regional level and ANNs are used to propagate these projected sea states obtained in deep water to the coast. The use of ANNs allows for the utilization of large amounts of data at a very low computational cost, and the use of Monte Carlo simulations enables the generation of future climate change projections at a regional level. The combination of the two methodologies results in a very accurate (MSE of 0.02 m and 1 s) and computationally inexpensive hybrid model that allows projections of coastal maritime climate considering climate change. This new methodology has been validated and applied in the Western Mediterranean for the long-term regime and for extreme events, obtaining increases in extreme events up to 1.5 m in wave height and up to 1.8 s in wave period by 2050. [Display omitted] [ABSTRACT FROM AUTHOR]