Seismic wave propagation and inversion with Neural Operators
This addresses a major bottleneck in seismological research by accelerating simulations, though it is incremental as it applies an existing machine learning paradigm to a specific domain.
The paper tackles the computational burden of solving seismic wave equations by using Neural Operators to learn general solutions, enabling rapid wavefield computation for any velocity structure or source location, and demonstrates a nearly 10x speedup over conventional methods for full waveform inversion.
Seismic wave propagation forms the basis for most aspects of seismological research, yet solving the wave equation is a major computational burden that inhibits the progress of research. This is exacerbated by the fact that new simulations must be performed when the velocity structure or source location is perturbed. Here, we explore a prototype framework for learning general solutions using a recently developed machine learning paradigm called Neural Operator. A trained Neural Operator can compute a solution in negligible time for any velocity structure or source location. We develop a scheme to train Neural Operators on an ensemble of simulations performed with random velocity models and source locations. As Neural Operators are grid-free, it is possible to evaluate solutions on higher resolution velocity models than trained on, providing additional computational efficiency. We illustrate the method with the 2D acoustic wave equation and demonstrate the method's applicability to seismic tomography, using reverse mode automatic differentiation to compute gradients of the wavefield with respect to the velocity structure. The developed procedure is nearly an order of magnitude faster than using conventional numerical methods for full waveform inversion.