Learned multiphysics inversion with differentiable programming and machine learning
This work provides a software tool for researchers in geophysics and related fields to tackle complex inverse problems more easily, though it is incremental as it builds on existing methods with new integrations.
The authors introduced the SLIM open-source framework for solving inverse problems in computational geophysics, such as seismic imaging, by integrating wave-equation physics, learned priors, and neural surrogates. They demonstrated its effectiveness with a scalable prototype for permeability inversion from time-lapse seismic data, achieving improved computational efficiency and accuracy in multiphysics simulations.
We present the Seismic Laboratory for Imaging and Modeling/Monitoring (SLIM) open-source software framework for computational geophysics and, more generally, inverse problems involving the wave-equation (e.g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations. By integrating multiple layers of abstraction, our software is designed to be both readable and scalable. This allows researchers to easily formulate their problems in an abstract fashion while exploiting the latest developments in high-performance computing. We illustrate and demonstrate our design principles and their benefits by means of building a scalable prototype for permeability inversion from time-lapse crosswell seismic data, which aside from coupling of wave physics and multiphase flow, involves machine learning.