We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Joint Inversion of Geophysical Data for Geologic Carbon Sequestration Monitoring: A Differentiable Physics‐Informed Neural Network Model.
- Authors
Liu, Mingliang; Vashisth, Divakar; Grana, Dario; Mukerji, Tapan
- Abstract
Geophysical monitoring of geologic carbon sequestration is critical for risk assessment during and after carbon dioxide (CO2) injection. Integration of multiple geophysical measurements is a promising approach to achieve high‐resolution reservoir monitoring. However, joint inversion of large geophysical data is challenging due to high computational costs and difficulties in effectively incorporating measurements from different sources and with different resolutions. This study develops a differentiable physics model for large‐scale joint inverse problems with reparameterization of model variables by neural networks and implementation of a differentiable programming approach of the forward model. The proposed physics‐informed neural network model is completely differentiable and thus enables end‐to‐end training with automatic differentiation for multi‐objective optimization by multiphysics data assimilation. The application to the Sleipner benchmark model demonstrates that the proposed method is effective in estimation of reservoir properties from seismic and resistivity data and shows promising results for CO2 storage monitoring. Moreover, the global parameters that are assumed to be uncertain in the rock‐physics model are accurately quantified by integration of a Bayesian neural network. Plain Language Summary: This study develops a complete inversion model for the joint quantification and interpretation of geophysical measurements from different sources for geologic carbon sequestration monitoring. By combining neural networks for model reparameterization and differentiable programming for inverse modeling, the developed approach accurately characterizes subsurface reservoirs, it identifies the migration of CO2 plume, and it quantifies global parameters that are uncertain in the forward models. One of the major advantages of this method is that all components in the model are seamlessly integrated and updated simultaneously. Moreover, the model can be easily deployed to high‐performance computing platforms, thereby providing a computationally efficient approach for large geophysical data. Therefore, the developed model illustrates promising results for geophysical subsurface monitoring. Key Points: A novel inverse model is developed by combining differentiable physics and deep neural networksThe developed model provides an accurate and efficient approach for the joint inversion of geophysical data from different sourcesThe inverted models accurately characterize subsurface properties and structures and identify the migration of CO2 plume
- Subjects
GEOLOGICAL carbon sequestration; CARBON sequestration; AUTOMATIC differentiation; BAYESIAN analysis; COMPUTING platforms; CARBON dioxide; INVERSE problems
- Publication
Journal of Geophysical Research. Solid Earth, 2023, Vol 128, Issue 3, p1
- ISSN
2169-9313
- Publication type
Article
- DOI
10.1029/2022JB025372