Data-Driven Connectionist Models for Performance Prediction of Low Salinity Waterflooding in Sandstone Reservoirs

Abstract

Low salinity waterflooding (LSWF) and its variants also known as smart water or ion tuned water injection have emerged as promising enhanced oil recovery (EOR) methods. LSWF is a complex process controlled by several mechanisms and parameters involving oil, brine, and rock composition. The major mechanisms and processes controlling LSWF are still being debated in the literature. Thus, the establishment of an approach that relates these parameters to the final recovery factor (RFf) is vital. The main objective of this research work was to use a number of artificial intelligence models to develop robust predictive models based on experimental data and main parameters controlling the LSWF determined through sensitivity analysis and feature selection. The parameters include properties of oil, rock, injected brine, and connate water. Different operational parameters were considered to increase the model accuracy as well. After collecting the relevant data from 99 experimental studies reported in the literature, the database underwent a comprehensive and rigorous data preprocessing stage, which included removal of duplicates and low-variance features, missing value imputation, collinearity assessment, data characteristic assessment, outlier removal, feature selection, data splitting (80–20 rule was applied), and data scaling. Then, a number of methods such as linear regression (LR), multilayer perceptron (MLP), support vector machine (SVM), and committee machine intelligent system (CMIS) were used to link 1316 data samples assembled in this research work. Based on the obtained results, the CMIS model was proven to produce superior results compared to its counterparts such that the root mean squared rrror (RMSE) values for both training and testing data are 4.622 and 7.757, respectively. Based on the feature importance results, the presence of Ca2+ in the connate water, Na+ in the injected brine, core porosity, and total acid number of the crude oil are detected as the parameters with the highest impact on the RFf. The CMIS model proposed here can be applied with a high degree of confidence to predict the performance of LSWF in sandstone reservoirs. The database assembled for the purpose of this research work is so far the largest and most comprehensive of its kind, and it can be used to further delineate mechanisms behind LSWF and optimization of this EOR process in sandstone reservoirs.

Missing Value Imputation Designs and Methods of Nature-Inspired Metaheuristic Techniques: A Systematic Review

“…For example, Bormann [3] suggested that 10% missing precipitation values of the calendar days are the threshold for removing the whole winter observations from the analysis. In contrast, Tatar et al [4] stated that a threshold of 50% missing features was excluded from the prediction of low salinity waterflooding, while imputation of mean value was applied for missing features below the missing threshold.…”

A Comparison between the Perturbed-Chain Statistical Associating Fluid Theory Equation of State and Machine Learning Modeling Approaches in Asphaltene Onset Pressure and Bubble Point Pressure Prediction during Gas Injection

“…In this research work, a threshold of 50% was considered according to previous research studies. 44 As shown in Table 1 , no parameter has more than 50% missing values, and therefore, they remain. For the other parameters, the missing values are replaced with the mean value of the parameter which is a widely used method for estimating missing values for numeric features.…”

“…A parameter must be eliminated if the parameter has many missing values or the percentage of missing values exceeds a certain threshold. In this research work, a threshold of 50% was considered according to previous research studies . As shown in Table , no parameter has more than 50% missing values, and therefore, they remain.…”

Asphaltene Precipitation Prediction during Bitumen Recovery: Experimental Approach versus Population Balance and Connectionist Models

“…Prior to imputation, it is necessary to ensure that there is a sufficient amount of data for imputation. If a column has more than 50% of data missing, then it is dropped, and the attempt for imputation is dismissed. , Missingno and Bilogur’s method was used to illustrate the missing values. Missing values from the database are shown in Figure .…”