Machine Learning for Prediction of CO2 Minimum Miscibility Pressure

Abstract

Abstract Minimum miscibility pressure (MMP) is defined as the minimum pressure at which the CO2 is dissolved in the oil phase inside the reservoir. Minimum miscibility pressure (MMP) plays a critical role in the CO2 injection process during miscible CO2 flooding. Experimentally, MMP is determined by slim-tube experiments, rising bubble method etc. However, experimental analysis is time consuming and can have high associated cost. Therefore, application of Artificial Intelligence (AI) techniques can assist in predicting the MMP based on the available input data. This will save significant time and efforts and predicted the MMP results faster and convenient way. Some authors have worked with AI tools to predict MMP, but the model proposed in this paper has a relatively lower error. Thus, the proposed model in this study is an improved model for the prediction of MMP for miscible CO2 flooding applications. A detailed optimization was carried out in this study for both ANN and ANFIS predictive tools. Single hidden layer with 12 neurons and ‘trainlm’ as training algorithm was found out after ANN optimization, whereas subtractive clustering with cluster radius of 0.3 was the optimum scenario for ANFIS technique. ANN prediction was overall better than ANFIS technique for the prediction of CO2 MMP.