BEACON: Bayesian Experimental design Acceleration with Conditional Normalizing flows $-$ a case study in optimal monitor well placement for CO$_2$ sequestration

TL;DR

This paper introduces BEACON, a Bayesian framework utilizing conditional normalizing flows for optimal well placement in CO$_2$ sequestration, improving monitoring efficiency under uncertainty with scalable, mathematically optimal design.

Contribution

The paper presents a novel Bayesian experimental design method combining fluid-flow simulations and generative neural networks for optimal well placement in CO$_2$ sequestration.

Findings

Method outperforms baseline in large-scale case studies

Scalable to three-dimensional domains

Provides mathematically optimal well placement strategies

Abstract

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.