Machine Learning Analyses of Low Salinity Effect in Sandstone Porous Media

Wang, Lei; Tian, Yan; Yao, Bowen; Yu, Xiangyu

doi:10.1615/jpormedia.2020033000

Cited by 10 publications

(8 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same goes for the studies that only used incremental oil recoveries. For example, Wang and Fu 20 and Wang et al 70 have used the incremental oil recoveries and provided no details about the RF i .…”

Section: Methodsmentioning

confidence: 99%

“…Despite the extensive application of AI in petroleum and chemical enginering, very few research works have investigated the performance of the LSWF in petroleum reservoirs via developing intelligent predictive models. ,− Different predictive tools, such as the ANN, adaptive neural fuzzy inference system (ANFIS), SVM, decision tree (DT), and random forests (RF), assist in the estimation of LSWF potential. Apart from these methods, other approaches, like the least squares support vector machine (LSSVM), which is a modified version of the SVM and extra tree (ET), are also proposed and utilized .…”

Section: Introductionmentioning

confidence: 99%

“…Several statistical parameters including mean squared error, coefficient of determination, and relative deviation aid in verification of the developed models . Based on the data-driven analysis of LSWF reported by Wang et al, several models were built such as the multiple linear regression (MLR), ANN, SVM, and RF to conduct a comparative analysis and present an optimum model with the best performance. The tertiary recovery factor, which ranges from 0 to 16.2%, was chosen as the output variable that has to be predicted.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2021

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2021

View full text Add to dashboard Cite

show abstract

“…This could be due to the inherent randomness of the porous micro-structures that demands for heuristic models and out-of-the-box solutions, such as ML (Meng & Li, 2018). The mainstream ML techniques that have been used in porous material research can be categorized as artificial neural networks (Akratos et al, 2009;Singh et al, 2011;ANNs), deep and convolution neural networks (DNNs and CNNs, respectively; Alqahtani et al, 2018;Santos et al, 2020;Wu et al, 2018), generative adversarial neural networks (GANs; Mosser et al, 2017Mosser et al, , 2018Shams et al, 2020), Bayesian (Mondal et al, 2010), ensemble learning (Al-Juboori & Datta, 2019;Nekouei & Sartoli, 2019), support vector machines (SVMs; Wang, Tian, Yao, & Yu, 2020), self-organizing maps (SOMs; Balam et al, 2018), and Gaussian processes (Crevillen-Garcia et al, 2017). Although, ANN is a general term to address many sorts of trainable network of nodes with any level of complexity in the structures, it is often used to refer to the shallow ANNs which is applicable in the present review, too.…”

Section: Data Science Domainsmentioning

confidence: 99%

“…Porous structures are naturally multi‐scale and due to the micro‐CT probing limitations, the porous media images lack sub‐micron information which plays an important role in evaluation of fluid transportation properties (Blunt, 2017; Shams et al., 2020). To overcome the aforementioned challenge, super resolution (SR) reconstructions are outstanding approaches which convert low resolution (LR) images to high resolution (HR) ones, or they can improve the quality of the LR images by reducing the difference error between LR and HR images (Karsanina et al., 2018; Karsanina & Gerke, 2018; Wang, Armstrong, & Mostaghimi, 2020; Wang et al., 2018; Wang, Tian, et al., 2020; Zhang, 2018). In other words, SR reconstruction enables us to generate HR images with desirable field of view and a realistic resemblance of real HR image (Keys, 1981; Zhang, 2018).…”

Section: Image Resolutionmentioning

confidence: 99%