Development of new models for predicting the oil recovery of sandstone reservoirs

Abstract

In this paper, a new correlation was developed (139 data sets) in this study to predict the oil recovery for sandstone solution gas drive reservoirs (SGDR) using NLMR with a coefficient of determination, R² of 0.90 (compared to 0.87 for Gulstad correlation). An artificial neural network (ANN) model was developed for this reservoir giving an R² of 0.92. A correlation was developed (111 data sets) in this study to predict the oil recovery for sandstone water drive reservoirs (SWDR) using NLMR with a coefficient of determination, R² of 0.93 (compared to 0.91 for American Petroleum Institute, API correlation). The developed ANN model for this reservoir gives an R² of 0.94.