Polynomial and nonparametric regressions for efficient predictive proxy metamodeling: Application through the CO2-EOR in shale oil reservoirs

An integrated optimization workflow combining Particle Swarm and Non-parametric Proxy Metamodels was adopted with reservoir simulation to optimize oil production in CO2-EOR in shale oil reservoirs. The cyclic-CO2 flooding optimization consisted of injection, soaking, and production durations over the prediction period. Also, Minimum bottom hole pressure, maximum oil production rate, and water cut were optimized for the production wells, and maximum bottom hole injection pressure and maximum gas injection rate were optimized for the injection wells. To reach the optimal solution, 176-candidate solutions were created as training experiments with 4 successive iterations of approximately 20 experiments each. The optimal solution increased oil production by 322,675 surface barrels. Next, a 2nd order polynomial regression, Multivariate Adaptive Regression Splines and Random Forest Model proxy models were constructed to metamodel the large reservoir simulator. The polynomial proxy has the least prediction error among other approaches to simplify the reservoir evaluation and optimization process.