Learned multiphysics inversion with differentiable programming and machine learning

TitleLearned multiphysics inversion with differentiable programming and machine learning
Publication TypeJournal Article
Year of Publication2023
AuthorsMathias Louboutin, Ziyi Yin, Rafael Orozco, Thomas J. Grady II, Ali Siahkoohi, Gabrio Rizzuti, Philipp A. Witte, Olav M√łyner, Gerard J. Gorman, Felix J. Herrmann
JournalThe Leading Edge
Volume42
Pagination452-516
Month07
KeywordsCCS, deep learning, Fourier neural operators, GCS, Imaging, inversion, invertible networks, machine learning, monitoring, multiphysics, Normalizing flows, SLIM, software, time-lapse
Abstract

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.

Notes

(The Leading Edge)

URLhttps://library.seg.org/doi/10.1190/tle42070474.1
Presentation
URL2
Citation Keylouboutin2023lmi