Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.27561

HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models

Ryoichiro Agata·Ayako Nakanishi·Dan Bassett·Satoru Baba·Yasuyuki Nakamura·Gou Fujie
View original source ↗Read source document ↗Export metadata ↓

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.

Explore related subjects

physics.geo-phcs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Ryoichiro Agata, Ayako Nakanishi, Dan Bassett, Satoru Baba, Yasuyuki Nakamura, Gou Fujie. 2026-10-20. HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity models. https://arxiv.org/abs/2610.27561

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Resonant lunar tides of Earth's core and basal magma ocean

Earth's magnetic field is generated by fluid motion in the liquid-metal core and has been active for billions of years. However, prior to the onset of inner-core growth, the sources of mechanical power that drove the geodynamo remain uncertain. During this period, the core may have been overlain by a basal magma ocean (BMO), creating two immiscible fluid layers separated by a density interface, beneath the solid mantle. We develop a theory for lunar tides in this core--BMO system, in which the tidal potential acts on the density contrast between the two layers. The resulting dynamics differ fundamentally from previous models driven by imposed deformation of the core's bounding envelope. In the inviscid limit, the response transitions from an equilibrium tide to an interfacial gravity wave as forcing frequency increases. The two regimes are separated by a resonance that occurs when the forcing frequency matches the natural frequency of the degree-2, order-2 interfacial mode. The inviscid core flow is formally identical to the canonical elliptical vortex, linking the problem to the theory of elliptical instability. Finite viscosity regularises the resonance, introduces phase lag and generates oscillatory boundary layers. Combined with parameterised models of lunar recession and BMO crystallisation, the theory predicts enhanced core-boundary ellipticity, core-flow speed, magnetic Reynolds number and instability metrics, particularly near resonance. These results identify a previously unexplored mechanism for tidally driven flow in differentiated planetary bodies and show that a BMO can enhance tidal coupling to the core, potentially contributing to dynamo action.

physics.geo-ph↗
arXiv2026

Dual Reverse Time Migration: Efficient Least-squares Imaging with Multiple Scattering in Dual Space

Least-squares reverse time migration (LSRTM) estimates a broadband reflectivity image by iteratively minimizing the data misfit. Despite its superior imaging performance over conventional reverse time migration (RTM), LSRTM is fundamentally limited by the first-order Born approximation and incurs a high computational cost due to the iterative solution of a source-dependent model-space Hessian. We propose dual RTM, a seismic imaging framework that reformulates the inverse problem in the dual space, where the optimization variable is the scattering information of all orders, rather than being limited to the first-order scattering of the Born approximation. Unlike LSRTM, which directly estimates the reflectivity model, dual RTM reconstructs the missing scattering data (dual variable) through a fixed-point iteration governed by the full wave equation, enabling the recovery of higher-order scattering and multiple reflections without repeated background velocity updates. Furthermore, dual RTM replaces the source-dependent model-space Hessian with a source-independent data-space Hessian. A hybrid time--frequency formulation enables this Hessian to be assembled and inverted once in the Fourier domain as an offline preprocessing step, reducing the online computational cost of each dual iteration to that of a single RTM application. Numerical experiments on challenging synthetic benchmarks demonstrate that dual RTM suppresses acquisition footprints, improves amplitude fidelity, and enhances deep imaging where primary reflections alone provide insufficient illumination. These results establish dual RTM as an efficient bridge between conventional RTM/LSRTM and nonlinear waveform inversion for high-resolution large-scale seismic imaging.

physics.geo-ph↗
arXiv2026

A Targeted Quadrature Framework for Simulating Large-Scale 3D Anisotropic Electromagnetic Measurements

A new efficient and accurate method is presented for simulating frequency-domain borehole electromagnetic (EM) measurements acquired in the presence of three-dimensional (3D) variations of anisotropic subsurface conductivity. The method is based on solving the quasi-static Maxwell equations with a finite-volume discretization via goal-oriented block-quadrature reduced-order modeling. Discretization is performed with a Lebedev grid that enables accurate and conservative solutions in the presence of any form of anisotropic electrical conductivity. Likewise, the method makes use of a new effective-medium approximation to locally account for non-conformal boundaries and large contrasts in electrical conductivity, especially in the vicinity of EM sources and receivers. The finite-volume discretization yields a large symmetric linear system of equations, which is reduced to a set of smaller structured problems via block Lanczos recursion. The formulation also enables the efficient calculation of the adjoint solution, which is necessary for gradient-based inversion of the measurements to estimate the associated spatial distribution of electrical conductivity, i.e., to solve the inverse problem. The method is applied and verified for borehole ultra-deep azimuthal resistivity (UDAR) measurements commonly used in subsurface geosteering and well navigation. Efficiency, robustness, and scalability are demonstrated using synthetic UDAR data generated in a three-dimensional formation inspired by North Sea geology. The numerical results confirm suitability for integration into real-time UDAR processing frameworks.

physics.geo-ph↗