Estimation of the CO2-oil minimum miscibility pressure for enhanced oil recovery

The authors' aim was to present new models based on artificial neural network (ANN) and two optimization algorithms including cuckoo optimization algorithm (COA) and teaching learning based optimization (TLBO) to predict the pure and impure CO₂ MMP. Thirty-four and 11 training and testing data sets were used to develop these models with following inputs: reservoir temperature, the mole percent of volatile oil components (C₁ and N₂), mole percent of intermediate oil components (C₂-C₄, CO₂, and H₂S), molecular weight of C₅₊ fraction in oil phase (MW_C5+) and mole percentage of CO₂, N₂, C₁, C₄, and H₂S in the injected gas. Statistical comparisons show that although two models yield acceptable results, the ANN-TLBO model has better performance with the lower mean absolute percentage error (2.6%) and standard deviation (3.37%) and the higher coefficient of determination (0.993). Moreover, among the available correlations, the Cronquist's (1978 Cronquist, C. (1978). Carbon dioxide dynamic miscibility with light reservoir oils. Fourth Annual U.S. DOE Symposium, Tulsa, Oklahoma. [Google Scholar]; corrected by Sebastian et al., 1985 Sebastian, H. M., Wenger, R. S., and Renner, T. A. (1985). Correlation of minimum miscibility pressure for impure CO2 streams. J. Pet. Technol. 37:2076–2082.[Crossref] , [Google Scholar]) correlations have better performance. Finally, the sensitivity analysis on the ANN-TLBO showed that MW_C5+ and reservoir temperature are the most influential parameters in determining the CO₂ MMP, respectively.