Probabilistic Tsunami Hazard Assessment Using Supervised Learning with Nonstationary Sea-Level Rise: Bali Case Study

¹ Water Resources Engineering Research Group, Faculty of Civil and Environmental Engineering, Bandung Institute of Technology, Jalan Ganesha No. 10, Bandung 40132, Indonesia
² Center for Coastal and Marine Development, Directorate of Research and Innovation, Bandung Institute of Technology, Jalan Ganesha No. 10, Bandung 40132, Indonesia
³ Master of Water Resources Management Study Program, Faculty of Civil and Environmental Engineering, Bandung Institute of Technology, Jalan Ganesha No. 10, Bandung 40132, Indonesia
⁴ Center for Water Resources Development, Directorate of Research and Innovation, Bandung Institute of Technology, Jalan Ganesha No. 10, Bandung 40132, Indonesia
⁵ Coastal Engineering Research Group, Faculty of Civil and Environmental Engineering, Bandung Institute of Technology, Jalan Ganesha No. 10, Bandung 40132, Indonesia

^* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Indonesia has been considered one of the most tsunami-prone countries due to its proximity to three major tectonic plates. Particularly, Bali is at a greater risk because it is a major tourist destination, since it is located between the Sunda Megathrust and the Flores Back-Arc Thrust. However, future tsunamis are expected to become more destructive due to the effects of sea-level rise. Therefore, this study aims to provide a framework for Probabilistic Tsunami Hazard Assessment (PTHA) in Bali considering nonstationary sea-level rise effects based on a supervised learning approach. Earthquake magnitude and sea-level rise are statistically analyzed, and earthquake parameters, including rupture width, length, and slip, are estimated using empirical scaling. Tsunami propagation analyses are performed considering several cases of earthquake magnitude and sea-level rise. Furthermore, Gaussian Process Regression (GPR) response surface models are developed to correlate the tsunami inundation depth to magnitude and sea-level rise to accelerate computation time. Finally, hazard curves are evaluated using a Monte Carlo simulation based on the uncertainty associated with earthquake magnitudes and sea-level rise. A case study in Denpasar is provided in the illustrative example, and the effects of sea-level rise and different earthquake rupture locations on tsunami hazard are evaluated.