HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models
Abstract
Rapid and accurate hypocenter determination based on three-dimensional (3D) seismic velocity models is essential for seismic monitoring in subduction zones, yet it remains computationally demanding. HypoNet Nankai, a hypocenter determination package that uses physics-informed neural network (PINN) travel-time inference for a realistic 3D P-wave velocity model of the Nankai Trough subduction zone, was designed to address this problem, but supported only P-wave arrival times. Here, we present HypoNet Nankai PS, which extends the framework to both P- and S-wave travel times. We first constructed an S-wave velocity model from the existing P-wave model using empirical conversion relations for marine sediments and the crust. Because the resulting S-wave velocity structure has lower velocities and therefore considerably steeper travel-time gradients, the original PINN training procedure designed for the P-wave velocity structure was insufficient. We therefore revised the training procedure by reconsidering the distribution of collocation points, the NN architecture, and the optimizer. Benchmark comparisons with the fast marching method showed that the revised approach substantially reduced the root-mean-square deviations for both P- and S-waves compared with the original algorithm. Recovery tests using synthetic earthquakes were also performed. When applied to 223 earthquakes recorded by DONET stations off the Kii Peninsula, the system yielded hypocenters generally consistent with the JMA catalog beneath the network, suggesting that the 3D velocity model captures travel-time variations accommodated by JMA's 1D model and station corrections. Farther seaward, the estimated hypocenters were substantially shallower than those in the JMA catalog and were located in the oceanic crust and uppermost mantle, consistent with previous relocations that used DONET data and 3D velocity models.
Related
- Self-attention summary networks for subsurface velocity-model building from common-image gathers
- How Sparse and How Noisy? Systematic Benchmarking of Inverse Physics-Informed Neural Networks for Manning Friction Estimation in Shallow Water Equations
- Latent Diffusion Modeling of Two- and Three-dimensional Fracture Networks with Sparse Observation Conditioning
- Cutting and shuffling control mixing in three-dimensional discrete fracture networks
- A 3D Vp and Vs Velocity Model for the Midland Basin, Texas
BibTeX
@misc{agata2026hyponet,
title = {{HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models}},
author = {Ryoichiro Agata and Ayako Nakanishi and Dan Bassett and Satoru Baba and Yasuyuki Nakamura and Gou Fujie},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27561},
eprint = {2610.27561},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27561},
}
RIS
TY - UNPB
TI - HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models
AU - Ryoichiro Agata
AU - Ayako Nakanishi
AU - Dan Bassett
AU - Satoru Baba
AU - Yasuyuki Nakamura
AU - Gou Fujie
PY - 2026
DA - 2026/10/20
PB - arXiv
DO - 10.48550/arxiv.2610.27561
UR - https://arxiv.org/abs/2610.27561
AB - Rapid and accurate hypocenter determination based on three-dimensional (3D) seismic velocity models is essential for seismic monitoring in subduction zones, yet it remains computationally demanding. HypoNet Nankai, a hypocenter determination package that uses physics-informed neural network (PINN) travel-time inference for a realistic 3D P-wave velocity model of the Nankai Trough subduction zone, was designed to address this problem, but supported only P-wave arrival times. Here, we present HypoNet Nankai PS, which extends the framework to both P- and S-wave travel times. We first constructed an S-wave velocity model from the existing P-wave model using empirical conversion relations for marine sediments and the crust. Because the resulting S-wave velocity structure has lower velocities and therefore considerably steeper travel-time gradients, the original PINN training procedure designed for the P-wave velocity structure was insufficient. We therefore revised the training procedure by reconsidering the distribution of collocation points, the NN architecture, and the optimizer. Benchmark comparisons with the fast marching method showed that the revised approach substantially reduced the root-mean-square deviations for both P- and S-waves compared with the original algorithm. Recovery tests using synthetic earthquakes were also performed. When applied to 223 earthquakes recorded by DONET stations off the Kii Peninsula, the system yielded hypocenters generally consistent with the JMA catalog beneath the network, suggesting that the 3D velocity model captures travel-time variations accommodated by JMA's 1D model and station corrections. Farther seaward, the estimated hypocenters were substantially shallower than those in the JMA catalog and were located in the oceanic crust and uppermost mantle, consistent with previous relocations that used DONET data and 3D velocity models.
ER -