BEACON: Bayesian Experimental design Acceleration with Conditional Normalizing flows $-$ a case study in optimal monitor well placement for CO$_2$ sequestration
This addresses the high-cost challenge of monitoring CO2 plumes in sequestration projects to prevent risks like leakage, though it appears incremental as an application of existing methods to a specific domain.
The paper tackles the problem of optimally placing a limited number of monitoring wells for CO2 sequestration to maximize effectiveness under budget constraints, by integrating fluid-flow solvers with generative neural networks in a Bayesian framework, and demonstrates optimal performance in a realistic case study compared to baseline placements.
CO$_2$ sequestration is a crucial engineering solution for mitigating climate change. However, the uncertain nature of reservoir properties, necessitates rigorous monitoring of CO$_2$ plumes to prevent risks such as leakage, induced seismicity, or breaching licensed boundaries. To address this, project managers use borehole wells for direct CO$_2$ and pressure monitoring at specific locations. Given the high costs associated with drilling, it is crucial to strategically place a limited number of wells to ensure maximally effective monitoring within budgetary constraints. Our approach for selecting well locations integrates fluid-flow solvers for forecasting plume trajectories with generative neural networks for plume inference uncertainty. Our methodology is extensible to three-dimensional domains and is developed within a Bayesian framework for optimal experimental design, ensuring scalability and mathematical optimality. We use a realistic case study to verify these claims by demonstrating our method's application in a large scale domain and optimal performance as compared to baseline well placement.