Modeling of Brine/CO2/Mineral Wettability Using Gene Expression Programming (GEP): Application to Carbon Geo-Sequestration

Carbon geo-sequestration (CGS), as a well-known procedure, is employed to reduce/store greenhouse gases. Wettability behavior one of the important parameters in geological CO2 sequestration process. Few models have been reported for characterizing contact angle brine/CO2/mineral system at different environmental conditions. In this study, smart machine learning model, namely Gene Expression Programming (GEP), was implemented model wettability ternary CO2, brine, and mineral under operating conditions, including salinity, pressure, temperature. The presented provided an accurate estimation receding, static, advancing angles brine/CO2 on various minerals, such calcite, feldspar, mica, quartz. A total 630 experimental data points were utilized establishing correlations. Both statistical evaluation graphical analyses performed show reliability performance developed models. results showed that GEP accurately predicted conditions few detected probably doubtful. average absolute percent relative error (AAPRE) proposed quartz obtained 5.66%, 1.56%, 14.44%, 13.93%, respectively, which confirm algorithm. Finally, investigation sensitivity analysis indicated salinity pressure had utmost influence range minerals. addition, effect column height illustrated. According impact residual structural trapping mechanisms during carbon process, outcomes can be beneficial precise prediction capacity these mechanisms.