A neural network-based surrogate model for efficient probabilistic tsunami inundation assessment

Probabilistic assessment and uncertainty evaluation of the inundation depth and distribution of tsunamis are critical for developing effective tsunami disaster preparedness and mitigation efforts. However, existing approaches based on nonlinear long wave theory, which is commonly used to analyze tsunami propagation and inundation in shallow waters, are computationally expensive, thereby limiting their practical application to probabilistic assessment, which requires numerous simulations. In this study, we propose an innovative method to reduce the analytical burden of probabilistic tsunami inundation assessment by building a surrogate model using deep neural networks (DNNs). Different inputs are tested, including the slip distribution of an earthquake fault, the initial water level distribution, and the water level distribution over time using linear long wave theory. The results show the possibility of predicting the tsunami inundation depths and inundation distributions with some accuracy directly from the slip distributions of earthquake faults rather than from information on initial water levels and subsequent tsunami water levels. These results indicate that, as long as the information on the slip distribution of a fault is available, the tsunami inundation depth and distribution can be instantly predicted using a surrogate model that has appropriately been trained on the outcomes of physical model simulations. This finding may constitute a breakthrough prediction method. If the probabilistic evaluation of the inundation depth and distribution or the evaluation of uncertainty can be easily performed, then local tsunami risk assessment and various disaster countermeasures based on such an assessment can be promoted.