Learned multiphysics inversion with differentiable programming and machine learning

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.

References in corpus (11)

• Score-Based Generative Modeling through Stochastic Differential Equations
• Fourier Neural Operator for Parametric Partial Differential Equations
• Real-time high-resolution CO${}_2$ geological storage prediction using nested Fourier neural operators
• A Differentiable Programming System to Bridge Machine Learning and Scientific Computing
• Model-Parallel Fourier Neural Operators as Learned Surrogates for Large-Scale Parametric PDEs
• Preconditioned training of normalizing flows for variational inference in inverse problems
• Learned coupled inversion for carbon sequestration monitoring and forecasting with Fourier neural operators
• De-risking geological carbon storage from high resolution time-lapse seismic to explainable leakage detection
• Compressive time-lapse seismic monitoring of carbon storage and sequestration with the joint recovery model
• Accelerating innovation with software abstractions for scalable computational geophysics
• SciAI4Industry -- Solving PDEs for industry-scale problems with deep learning

Cited by in corpus (5)

• WISE: full-Waveform variational Inference via Subsurface Extensions
• Solving multiphysics-based inverse problems with learned surrogates and constraints
• An uncertainty-aware Digital Shadow for underground multimodal CO2 storage monitoring
• WISER: multimodal variational inference for full-waveform inversion without dimensionality reduction
• Time-lapse full-waveform permeability inversion: a feasibility study