The Dense Ocean-floor Network for Earthquakes and Tsunamis (DONET) was recently installed to monitor tsunamis in the Nankai trough.
In this study, an advanced tsunami prediction model using Gaussian process regression that is suitable for seafloor pressure observations is proposed.
The maximum tsunami height and tsunami arrival time observed at seafloor pressure sensors are used as explanatory variables.
Because tsunami data observed by ocean observatories are insufficient for constructing Gaussian regression relationships, numerical tsunami simulations are used for learning and validation.
After tsunami detection by DONET, the accuracy of tsunami height prediction along the coast is improved by considering the tsunami arrival time at seafloor pressure sensors. The proposed model enables rapid and effective estimation of coastal tsunami heights.