Key points are not available for this paper at this time.
ABSTRACT: In this paper, an innovative method comprising of multi-tiered analysis has been developed to leverage advanced Machine Learning (ML) techniques to process passive seismic monitoring data acquired over a three-year injection period into a CO2 storage site in the Illinois Basin for potential fracture/fault analysis. The study is aimed at contributing to monitoring design and de-risking operation for carbon capture, utilization, and storage (CCUS) and improving monitoring, verification, and accounting (MVA) of injected subsurface CO2. Information on fractures from well logs and core data is integrated together to develop a comprehensive understanding of how these fractures correlate with the rock petrophysical properties. The fracture networks obtained from this approach can 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, the proposed methodology is potentially applicable to oil and gas assets as well as geothermal development, operations, and monitoring. 1. INTRODUCTION Injecting significant volume of anthropogenic carbon dioxide (CO2) into geological reservoirs is one of the piloted practices for greenhouse gas reduction. These operations have gained considerable traction in the last decade as a viable option to reduce the long-term environmental footprint. 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. This study is part of the Science-informed Machine Learning (ML) for Accelerating Real-Time Decisions in Subsurface Applications (SMART) Initiative which have funded by the US Department of Energy Carbon Storage program to transform our ability to make better, informed decisions related to the subsurface through real-time visualization, forecasting, and virtual learning. The outcomes of the SMART Initiative are science-informed machine learning-based tools that can be applied at carbon storage sites throughout the nation and the world to 1) improve the ability to consolidate technical knowledge, site-specific characterization information, and real-time data in a digestible way; 2) enable the optimization of carbon storage reservoirs by creating a capability for "real-time" forecasting of carbon storage reservoir behavior; and 3) improve the ability to understand and communicate subsurface behavior during carbon storage operations to non-experts. The ultimate objectives aim in helping accelerate the deployment of field scale carbon storage in the US and the world.
Liu et al. (Sun,) studied this question.