Rapid earthquake location using physics-informed neural networks and 3d wave models
HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models
Machine Learning
Summary
Finding where an earthquake starts quickly and accurately is hard because of complex underground structures. The authors improved a computer method called HypoNet Nankai by adding both P-wave and S-wave data, which travel differently underground. They made new adjustments to the learning process to handle these waves better, resulting in more precise earthquake locations near the Nankai Trough. When tested on real data, their system found earthquake sources close to existing catalogs but sometimes gave shallower depths, matching other detailed studies.
What this means in practice
- •For seismic monitoring teams: Use the combined P- and S-wave travel-time inference from HypoNet Nankai PS to quickly locate earthquake hypocenters in complex 3D velocity structures for better regional seismic hazard assessment.
- •For oil and gas exploration engineers: Incorporate physics-informed neural network travel-time calculations to improve the precision of locating microseismic events during reservoir monitoring in marine sediment and crustal environments.
Authors
Ryoichiro Agata, Ayako Nakanishi, Dan Bassett, Satoru Baba, Yasuyuki Nakamura, Gou Fujie
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.