Probabilistic Tsunami Heights Model using Bayesian Machine Learning

Abstract

Song, M.-J. and Cho, Y.-S., 2020. Probabilistic tsunami heights model with Bayesian machine learning. In: Malvárez, G. and Navas, F. (eds.), Global Coastal Issues of 2020. Journal of Coastal Research, Special Issue No. 95, pp. 1291–1296. Coconut Creek (Florida), ISSN 0749-0208.Tsunamis, which are long-period oceanic waves, are known as catastrophic disasters and can cause large losses of human life, as well as property damage. To date, tsunami research has focused on developing numerical models to predict accurate tsunami heights and run-up heights, because hydraulic experiments are associated with high costs for laboratory installation and maintenance. Recently, artificial intelligence (AI) has been progressed, demonstrating enhanced performances in science and engineering fields. This study explored the use of AI to estimate maximum tsunami heights. Bayesian machine learning, a neural network method, was employed, and numerical simulation was performed for historical and probable maximum tsunami events.