Machine Learning Application for CCUS Carbon Storage: Fracture Analysis and Mapping in the Illinois Basin

Abstract

Abstract A significant volume of anthropogenic carbon dioxide (CO2) is being injected into geological reservoirs at multiple locations throughout the United States. These operations have gained considerable traction in the last decade as a viable option to reduce the long-term environmental footprint of greenhouse gas emissions. However, monitoring the storage reservoir to ensure safe and long-term storage of CO2 for de-risk operations and storage management is undergoing dynamic shifts, expanding opportunities for implementing innovative techniques and applications, especially for the commercial-scale deployment. In this paper, an innovative method comprising multi-tiered analysis has been developed to leverage advanced machine learning (ML) techniques to process passive seismic monitoring data acquired over the two-year injection period along with pumping/injection pressure and rate in the Illinois Basin for potential fracture/fault analysis. Moreover, well log data including imaging logs and core test results are also integrated in the study to add another angle of the understanding for fracture. This study is aimed at contributing to the risk assessment and monitoring design for carbon capture, utilization and storage (CCUS). As a continuation of this effort, we intend to compare the spatial distribution of fractures with the available well logs and core data to deduce a comprehensive understanding of how these fractures correlate with the rock petrophysical properties. The fracture networks obtained from this study would directly benefit field operations and reservoir management decision-making for CCUS, which include the dynamic injection scheduling/workover, risk assessment, and further monitoring design. Furthermore, for ecosystem benefits, the proposed methodology is potentially applicable to oil and gas and renewable assets, such as geothermal development for their fracture-based monitoring and risk reduction as well.