Machine Learning Applications in Analyzing the Role of Shale Barriers and Baffles for CO2 Storage

Conference · Mon Aug 05 04:00:00 EDT 2024

DOI:https://doi.org/10.2172/2426374· OSTI ID:2426374

Carr, Timothy ^[1]; Fathi, Ebrahim ^[1]; Iyegbekedo, Ikponmwosa ^[1]

---

1. West Virginia University (WVU)

This study uses machine learning to analyze microseismic data from the Illinois Basin Decatur Project (IBDP) and quantify CO₂ plume extents. By leveraging well logs, microseismic records, and CO₂ injection metrics, the research predicts subsurface CO₂ plume dynamics. Findings show vertical clustering of microseismic events near the injection well, with CO₂ periodically breaching barriers due to buoyancy. K-Means clustering performed best, achieving the highest Silhouette Score and lowest Davies-Bouldin Index. This capability is crucial for real-time monitoring and management of CO₂ sequestration sites, validated against physical models and IBDP data, reinforcing CO₂ geological sequestration's viability and enhancing management tools.

• Research Organization: National Energy Technology Laboratory (NETL), Pittsburgh, PA, Morgantown, WV, and Albany, OR (United States)
• Sponsoring Organization: USDOE Office of Fossil Energy and Carbon Management (FECM), Office of Carbon Management (FE-20)
• OSTI ID: 2426374
• Country of Publication: United States
• Language: English