Learned multiphysics inversion with differentiable programming and machine learning
Open Access
- 1 July 2023
- journal article
- research article
- Published by Society of Exploration Geophysicists in The Leading Edge
- Vol. 42 (7) , 474-486
Abstract
We present the Seismic Laboratory for Imaging and Modeling/Monitoring 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, the software is designed to be both readable and scalable, allowing researchers to easily formulate problems in an abstract fashion while exploiting the latest developments in high-performance computing. The design principles and their benefits are illustrated and demonstrated 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.Keywords
All Related Versions
This publication has 22 references indexed in Scilit:
- Seismic Tomography Using Variational Inference MethodsJournal of Geophysical Research: Solid Earth, 2020
- Compressive least-squares migration with on-the-fly Fourier transformsGeophysics, 2019
- A large-scale framework for symbolic implementations of seismic inversion algorithms in JuliaGeophysics, 2019
- Devito (v3.1.0): an embedded domain-specific language for finite differences and geophysical explorationGeoscientific Model Development, 2019
- Flux: Elegant machine learning with JuliaJournal of Open Source Software, 2018
- Full-waveform inversion, Part 3: OptimizationThe Leading Edge, 2018
- 20 Years of Monitoring CO2-injection at SleipnerEnergy Procedia, 2017
- SymPy: symbolic computing in PythonPeerJ Computer Science, 2017
- Julia: A Fresh Approach to Numerical ComputingSIAM Review, 2017
- Madagascar: open-source software project for multidimensional data analysis and reproducible computational experimentsJournal of Open Research Software, 2013