Wavefield reconstruction inversion via physics-informed neural networks

Abstract

Wavefield reconstruction inversion (WRI) formulates a PDE-constrained optimization problem to reduce cycle skipping in full-waveform inversion (FWI). WRI often requires expensive matrix inversions to reconstruct frequency-domain wavefields. Physics-informed neural network (PINN) uses the underlying physical laws as loss functions to train the neural network (NN), and it has shown its effectiveness in solving the Helmholtz equation and generating Green's functions, specifically for the scattered wavefield. By including a data-constrained term in the loss function, the trained NN can reconstruct a wavefield that simultaneously fits the recorded data and satisfies the Helmholtz equation for a given initial velocity model. Using the predicted wavefields, we rely on a small-size NN to predict the velocity using the reconstructed wavefield. In this velocity prediction NN, spatial coordinates are used as input data to the network and the scattered Helmholtz equation is used to define the loss function. After we train this network, we are able to predict the velocity in the domain of interest. We develop this PINN-based WRI method and demonstrate its potential using a part of the Sigsbee2A model and a modified Marmousi model. The results show that the PINN-based WRI is able to invert for a reasonable velocity with very limited iterations and frequencies, which can be used in a subsequent FWI application.

References in corpus (16)

• DGM: A deep learning algorithm for solving partial differential equations
• Solving high-dimensional partial differential equations using deep learning
• Fourier Neural Operator for Parametric Partial Differential Equations
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Deep-Learning Inversion of Seismic Data
• Modeling the Dynamics of PDE Systems with Physics-Constrained Deep Auto-Regressive Networks
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Solving the acoustic VTI wave equation using physics-informed neural networks
• Deep Learning Inversion of Electrical Resistivity Data
• PINNeik: Eikonal solution using physics-informed neural networks
• Data-driven discovery of PDEs in complex datasets
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• A penalty method for PDE-constrained optimization in inverse problems
• Fast approximate simulation of seismic waves with deep learning
• Learning Functions: When Is Deep Better Than Shallow
• PINNtomo: Seismic tomography using physics-informed neural networks

Cited by in corpus (2)

• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Physics-driven Deep Learning Inversion for Direct Current Resistivity Survey Data