Estimation of Minimum Miscibility Pressure in Impure/Pure N2 Based Enhanced Oil Recovery Process: A Comparative Study of Statistical and Machine Learning Algorithms

Minimum miscibility pressure (MMP) prediction plays an important role in design and operation of nitrogen based enhanced oil recovery processes. In this work, a comparative study of statistical and machine learning methods used for MMP estimation is carried out. These methods include weighted k-nearest neighbors, wavelet neural network, general regression neural network, extreme learning machine, regression trees (RTs), random forest, bagging RTs, boosting RTs and Gaussian process regression. Most of the predictive models developed in this study exhibited superior performance over predictive models reported in literature.