HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks

Abstract

We introduce a scheme for probabilistic hypocenter inversion with Stein variational inference. Our approach uses a differentiable forward model in the form of a physics informed neural network, which we train to solve the Eikonal equation. This allows for rapid approximation of the posterior by iteratively optimizing a collection of particles against a kernelized Stein discrepancy. We show that the method is well-equipped to handle highly multimodal posterior distributions, which are common in hypocentral inverse problems. A suite of experiments is performed to examine the influence of the various hyperparameters. Once trained, the method is valid for any seismic network geometry within the study area without the need to build travel time tables. We show that the computational demands scale efficiently with the number of differential times, making it ideal for large-N sensing technologies like Distributed Acoustic Sensing. The techniques outlined in this manuscript have considerable implications beyond just ray-tracing procedures, with the work flow applicable to other fields with computationally expensive inversion procedures such as full waveform inversion.

Updating to accepted version of the paper

Cited by in corpus (16)

• Physics-Informed Neural Operator for Learning Partial Differential Equations
• QuakeFlow: A Scalable Machine-learning-based Earthquake Monitoring Workflow with Cloud Computing
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• 3D Bayesian Variational Full Waveform Inversion
• Bayesian Physics-Informed Neural Networks for the Subsurface Tomography based on the Eikonal Equation
• Deep Neural Helmholtz Operators for 3D Elastic Wave Propagation and Inversion
• Amortized Variational Inference: A Systematic Review
• Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Variational Prior Replacement in Bayesian Inference and Inversion
• Annealed Stein Variational Gradient Descent for Improved Uncertainty Estimation in Full-Waveform Inversion
• Surface wave dispersion inversion using an energy likelihood function
• Emerging Directions in Geophysical Inversion
• Modeling Global Surface Dust Deposition Using Physics-Informed Neural Networks
• VIP -- Variational Inversion Package with example implementations of Bayesian tomographic imaging
• Full-waveform earthquake source inversion using simulation-based inference