Bayesian Physics-Informed Neural Networks for the Subsurface Tomography based on the Eikonal Equation

Abstract

The high cost of acquiring a sufficient amount of seismic data for training has limited the use of machine learning in seismic tomography. In addition, the inversion uncertainty due to the noisy data and data scarcity is less discussed in conventional seismic tomography literature. To mitigate the uncertainty effects and quantify their impacts in the prediction, the so-called Bayesian Physics-Informed Neural Networks (BPINNs) based on the eikonal equation are adopted to infer the velocity field and reconstruct the travel-time field. In BPINNs, two inference algorithms including Stein Variational Gradient Descent (SVGD) and Gaussian variational inference (VI) are investigated for the inference task. The numerical results of several benchmark problems demonstrate that the velocity field can be estimated accurately and the travel-time can be well approximated with reasonable uncertainty estimates by BPINNs. This suggests that the inferred velocity model provided by BPINNs may serve as a valid initial model for seismic inversion and migration.

References in corpus (8)

• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Uncertainty Quantification in Scientific Machine Learning: Methods, Metrics, and Comparisons
• Bayesian Neural Networks: An Introduction and Survey
• PINNeik: Eikonal solution using physics-informed neural networks
• EikoNet: Solving the Eikonal equation with Deep Neural Networks
• HypoSVI: Hypocenter inversion with Stein variational inference and Physics Informed Neural Networks
• PINNtomo: Seismic tomography using physics-informed neural networks
• Laplace HypoPINN: Physics-Informed Neural Network for hypocenter localization and its predictive uncertainty

Cited by in corpus (1)

• A Critical Review of Physics-Informed Machine Learning Applications in Subsurface Energy Systems