Utilizing Artificial Intelligence Techniques for Modeling Minimum Miscibility Pressure in Carbon Capture and Utilization Processes: A Comprehensive Review and Applications

Abstract

The carbon dioxide (CO 2 ) based enhanced oil recovery methods (EORs) are considered among the promising techniques for increasing the recovery factor from mature oil reservoirs and reducing the amount of CO 2 emission in the atmosphere. Determining the minimum miscibility pressure (MMP) of CO 2 − oil systems is a crucial step for successfully implementing CO 2 − EOR processes. Therefore, various approaches have been proposed for determining this key parameter. However, the laboratory tests are expensive and timeconsuming, while most available correlations present moderate accuracy. To address these shortcomings, various studies have applied artificial intelligence (AI) techniques to model the MMP of the CO 2 − oil systems. In this study, we reviewed the published works for predicting the MMP of the CO 2 − oil systems using AI-based models. Our analyses revealed the robustness of these techniques in modeling MMP. In this context, it was noticed that more than 70 AI-based paradigms have been utilized for estimating the MMP of CO 2 − oil systems. Among the applications, the hybrid schemes combining machine learning and nature-inspired algorithms (ML-NIA) take the top spot, accounting for 27% of applications. Additionally, the investigation demonstrated that the artificial neural network (ANN) is the most utilized ML method in the modeling phase, while the genetic algorithm (GA) is the most widely applied NIA for improving ML performance. In the second part of this study, we suggest an updated correlation based on gene expression programming (GEP) for the accurate prediction of MMP of CO 2 − oil systems. Our proposed explicit correlation yielded excellent predictive performance, achieving overall root-mean-square error and determination coefficient (R 2 ) values of 0.9253 and 09713, respectively. These promising statistical metrics enabled the newly updated GEP-based correlation to outperform the preexisting models. Besides, the physical validity and interpretability of the proposed correlation were proven using the trend analysis and the Shape Dependence Analysis plot, respectively. Lastly, the findings of this study provide a dual benefit, the review and the illustration of the published studies on applying AI techniques for modeling the MMP of the CO 2 − oil systems; and second, the newly implemented GEP-based correlation can significantly enhance the effective prediction of the MMP in CO 2 -oil systems, thus, facilitating the simulation of various CO 2 − based EOR processes.