data assimilation 1fault slip forecasting 1frictional heterogeneity 1geodetic observations 1physics-informed neural networks 1slow slip events 1
From the 1 of 3 linked papers with an AI index.
3 papers
physics.geo-ph2026
PINN-based short-term forecasting of fault slip evolution during the 2010 slow slip event in the Bungo Channel, Japan
Masayuki Kano, Rikuto Fukushima
The paper presents a physics-informed neural network (PINN) framework that assimilates geodetic data and fault mechanics with spatially heterogeneous friction to forecast short‑ter…
physics.geo-ph2026
Physics-informed deep learning links geodetic data and fault friction
Rikuto Fukushima, Masayuki Kano, Kazuro Hirahara +1
Fault slip modeling, based on laboratory-derived friction laws, has significantly enhanced our understanding of fault mechanics. Agreement between model predictions and observation…
physics.geo-ph2025
Three-dimensional crustal deformation analysis using physics-informed deep learning
Tomohisa Okazaki, Takeo Ito, Kazuro Hirahara +3
Earthquake-related phenomena such as seismic waves and crustal deformation impact broad regions, requiring large-scale modeling with careful treatment of artificial outer boundarie…