Evaluation of caprock integrity for underground storage of CO2 in depleted oil and gas reservoirs using machine learning approaches.

Aminaho, Efenwengbe Nicholas; Sanaee, Reza; Faisal, Nadimul

Abstract

Carbon Dioxide (CO2) geosequestration represents one of the most promising options for reducing atmospheric emissions of CO2. Caprock integrity - ascertained based on the petrophysical and geomechanical properties of caprock - is vital to ensure safe and sustainable storage of CO2 (Liu et al., 2020). Shale and carbonate rocks are typical caprock for CO2 geological storage, but their failure behaviours have not been fully understood due to their severe heterogeneity and anisotropy (Liu et al., 2020). It is therefore vital to apply machine learning techniques in order to understand caprock behaviour under several conditions. No other study so far has focused on caprock integrity using machine learning to select the best depleted petroleum reservoirs for CO2 storage, based on caprock mechanical and petrophysical properties. The aim of this research is to evaluate caprock integrity under cyclic stress loadings based on variation in pressure and CO2 injection temperature.

Citation

AMINAHO, E.N., SANAEE, R. and FAISAL, N. 2022. Evaluation of caprock integrity for underground storage of CO2 in depleted oil and gas reservoirs using machine learning approaches. Presented at the Applicability of hydrocarbon subsurface workflows to CCS conference, 28-29 April 2022, London, UK.

• Presentation Conference Type: Poster
• Conference Name: 2022 Applicability of hydrocarbon subsurface workflows to CCS conference
• Start Date: Apr 28, 2022
• End Date: Apr 29, 2022
• Deposit Date: Apr 27, 2022
• Publicly Available Date: May 10, 2022
• Peer Reviewed: Peer Reviewed
• Keywords: Carbon storage; Carbon capture; Caprock analysis; Machine learning
• Public URL: https://rgu-repository.worktribe.com/output/1650066