Eikonal Tomography With Physics?Informed Neural Networks: Rayleigh Wave Phase Velocity in the Northeastern Margin of the Tibetan Plateau

We present a novel eikonal tomography approach using physics-informed neural networks (PINNs) for Rayleigh wave phase velocities based on the equation. The PINN (pinnET) network utilizes deep as universal function approximators and extracts traveltimes of medium during optimization process. Whereas classical uses generic non-physics interpolation regularization step to reconstruct traveltime surfaces, optimizing parameters in pinnET means solving physics constrained surface reconstruction inversion tackling measurement noise satisfying physics. demonstrate this by applying it 25 s data from ChinArray II sampling northeastern Tibetan plateau. validate our results comparing them conventional same area find good agreement.