Application of machine learning in the determination of rock brittleness for CO2 geosequestration.

Aminaho, Efenwengbe Nicholas; Hossain, Mamdud; Faisal, Nadimul Haque; Sanaee, Reza

Abstract

The underground storage of carbon dioxide (CO2), also called CO2 geosequestration, represents one of the most promising options for reducing greenhouse gases in the atmosphere. However, fluid-rock interactions in reservoir and cap rocks before and during CO2 geosequestration alter their mineralogical composition, and consequently, their brittleness index which is paramount in determining the suitability of formations for CO2 geosequestration. Therefore, it is important to monitor the brittleness of reservoir and cap rocks, to ascertain their integrity for CO2 storage. In this study, an algorithm was developed to generate numerical simulation datasets for a more reliable machine learning model development, and an artificial neural network (ANN) model was developed to evaluate the brittleness index of rocks using data from numerical simulations of CO2 geosequestration in sandstone and carbonate reservoirs, overlain by shale caprock. The model was developed using Python programming language. The model developed in this study predicted the brittleness index of rocks with an R2 value greater than 99%, and mean absolute percentage error (MAPE) less than 0.6% on the training, validation, and testing datasets. Hence, the model predicts the brittleness index of rocks with high accuracy. The findings of the study revealed that the geochemical composition of formation fluids impacts the brittleness index of rocks. In terms of feature importance in predicting the brittleness index of rocks, the concentrations of SiO2 (aq), SO42, K+, Ca2+, and O2 (aq) have a stronger impact on the brittleness of rocks considered in this study.

Citation

AMINAHO, E.N., HOSSAIN, M., FAISAL, N.H. and SANAEE, R. 2025. Application of machine learning in the determination of rock brittleness for CO2 geosequestration. Machine learning with applications [online], 20, article number 100656. Available from: https://doi.org/10.1016/j.mlwa.2025.100656

• Journal Article Type: Article
• Acceptance Date: Apr 15, 2025
• Online Publication Date: May 5, 2025
• Publication Date: Jun 30, 2025
• Deposit Date: May 5, 2025
• Publicly Available Date: May 5, 2025
• Journal: Machine learning with applications
• Electronic ISSN: 2666-8270
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 20
• Article Number: 100656
• DOI: https://doi.org/10.1016/j.mlwa.2025.100656
• Keywords: Geosequestration; Formations; Brittleness; Algorithm; Artificial neural network; Concentration
• Public URL: https://rgu-repository.worktribe.com/output/2829743