Performance evaluation of ferro-fluids flooding in enhanced oil recovery operations based on machine learning

Abstract

The process of enhanced oil recovery (EOR) and core flooding involves various challenges such as preserving cores, configuring experiment setup, scaling from the laboratory to the field, interpreting experimental data, handling interactions between multiple EOR agents, and performing cost-effective evaluations. However, recent advancements in artificial intelligence and deep learning have facilitated the prediction of EOR efficiency, simplifying the process while saving time and money - two vital aspects of petroleum engineering. This study employed deep learning to determine the impact of ferro-fluids on EOR efficiency, which reduces excessive laboratory analysis costs and saves time. The findings may aid in optimizing injectable materials for future EOR projects. Four machine learning (ML) algorithms were utilized to predict the efficacy of ferro-fluids in carbonate and sandstone core flooding: support vector machine (SVM) for classification, multilayer perceptron (MLP), radial basis function (RBF), artificial neural network (ANN), and adaptive neuro-fuzzy inference system (ANFIS) for regression. The models were trained initially, followed by creating a set of validating measurements through classification to determine the regression trend of ferro-fluids. The SVM accurately classified all data points and the resulting regressions were satisfactory, with MLP and ANFIS producing R2 values of 0.9957 and 0.9922, respectively.