Artificial Intelligence in Coastal Engineering: Application to Climate Change Studies

Portillo, J.N.; Olalde Rodríguez, J.; del Campo, J.M., and Negro Valdecantos, V., 2024. Artificial Intelligence in coastal engineering: Application to climate change studies. In: Phillips, M.R.; Al-Naemi, S., and Duarte, C.M. (eds.), Coastlines under Global Change: Proceedings from the International Coastal Symposium (ICS) 2024 (Doha, Qatar). Journal of Coastal Research, Special Issue No. 113, pp. 180-184. Charlotte (North Carolina), ISSN 0749-0208. Artificial Intelligence (AI) has emerged strongly in society in recent years, disrupting traditionally established models. While AI techniques have long been utilized in other scientific domains, their adoption in coastal engineering, our specific field, remains relatively uncommon. Numerical models, known for their accuracy but high computational cost, continue to dominate. This work reviews AI techniques currently utilized in coastal engineering, analyzing the potential applications of various AI methodologies in ocean and coastal engineering. We then apply one of the most widely used AI methodologies, Artificial Neural Networks (ANNs), to study the adaptation of coastal structures to climate change, with a focus on the port of Valencia. The effectiveness of ANNs has been demonstrated in both, the propagation of wave climate, and the analysis of coastal structure dynamics. Notably, ANNs have outperformed traditional models in predicting wave peak periods, achieving a correlation coefficient of 0.96 and an error of 1.00 seconds, compared to 0.72 and 6.2 seconds, respectively, for the SWAN model. Finally, we analyze the weaknesses of ANNs and suggest potential future research lines.