Applying a sophisticated approach to predict CO2 solubility in brines: application to CO2 sequestration

Abstract

Specification of CO₂ and brine phase behaviour plays a vital role in CO₂ sequestration and CO₂ reduction from atmosphere to deep saline aquifers. Because CO₂ solubility in brines determine how much carbon can be stored in deep saline aquifers. To tackle the referred issue, high precise model with low uncertainty parameters called ‘least square support vector machine (LS-SVM)’ was executed to predict CO₂–brine solubility. The proposed intelligent-based approach is examined by using extensive experimental data reported in open literature. Results obtained from the proposed numerical solution model were compared with the relevant experimental CO₂–brine solubility data. The average relative absolute deviation between the model predictions and the relevant experimental data was found to be <0.1% for LS-SVM model.