Our work focuses on the recently emergent Physics-Informed Neural Network (PINN), which seamlessly integrates data while ensuring that model outcomes satisfy rigorous physical constraints.
We develop a multi-network PINN for both the forward problem and direct inversion of nonlinear fault friction parameters, constrained by the physics of motion in the solid Earth, with implications for seismic hazard assessment.
#physics-informed-neural-network #earthquake-modeling #seismology #machine-learning #seismic-hazard-assessment
Collection
[
|
...
]