Hybrid connectionist models to assess recovery performance of low salinity water injection

The low salinity water injection (LSWI) is one of the emerging enhanced oil recovery techniques to improve both microscopic and macroscopic displacement efficiencies by creating a new streamline in petroleum reservoirs. While experimental studies are tedious, costly, and time-consuming, the smart connectionist tools are more reliable and cost-effective approaches to predict oil recovery factor (RF) without considerations of governing equations and physics behind production mechanisms in oil reservoirs. The main objective of this study is to investigate the data-driven model performance and variable contribution while predicting RF of LSWI processes. We introduce connectionist models using hybridized least squares support vector machine (LSSVM) with global optimization technique of coupled simulated annealing (CSA), and adaptive network-based fuzzy inference system (ANFIS). The extremely randomized tree or extra tree (ET) tool is also applied to forecast the RF and investigate the parameter contribution in the employed model. The model performance is examined using statistical parameters, including coefficient of determination, relative error, mean absolute percentage error, and mean squared error. According to the results, the ET and hybridized LSSVM-CSA models perform better than the ANFIS model in estimating RF. Utilizing the ET smart model, the total dissolved salts (TDS, ppm) is the most influential parameter, while the fluid injection rate has the minimum importance in the determination of RF. The current research confirms that LSSVM-CSA and ET techniques are able to obtain RF of LSWI with high accuracy and reliability, which can be used by researchers and engineers for better management of oil reservoirs under LSWI.