Application of hybrid support vector regression artificial bee colony for prediction of MMP in CO2-EOR process

Amar, Menad Nait; Zerhouni, Noureddine

doi:10.1016/j.petlm.2018.08.001

Cited by 44 publications

(20 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the literature, there are several attempts with different procedures to improve the SVR performance by appropriated choosing of these hyperparameters 9–11,59–61 . Nature‐inspired algorithms are among those different procedures that were employed to select the hyperparameters of SVR 11–20,62 . However, in all these existing procedures regarding the selection of hyperparameters, there is no attempt to perform feature selection simultaneously.…”

Section: The Proposed Algorithmmentioning

confidence: 99%

“…Nature‐inspired algorithms, which they developed by drawing inspiration from nature, have attracted considerable interest and achieved competitive results when solving optimization problems including hyperparameters tuning problem 9–11 and feature selection. In the literature, there are numerous studies on tuning the hyperparameters of SVR using nature‐inspired algorithms 11–20 . In recent days, researchers are developing several new nature‐inspired algorithms for improving and enhancing exploration and exploitation of the existing algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Harris hawks optimization algorithm for hyperparameters estimation and feature selection in v‐support vector regression based on opposition‐based learning

Ismael

Qasim

Algamal

2020

Journal of Chemometrics

View full text Add to dashboard Cite

Many real problems have been solved by support vector regression, especially v‐support vector regression (v‐SVR), but there are hyperparameters that usually needed to tune. In addition, v‐SVR cannot perform feature selection. Nature‐inspired algorithms have been used as a feature selection and as hyperparameters estimation procedure. In this paper, the opposition‐based learning Harris hawks optimization algorithm (HHOA‐OBL) is proposed to optimize the hyperparameters of the v‐SVR with embedding the feature selection simultaneously. The experimental results over four datasets show that the HHOA‐OBL outperforms the standard Harris hawks optimization algorithm, grid search, and cross‐validation methods, in terms of prediction, number of selected features, and running time. Besides, the experimental results of the HHOA‐OBL confirm the efficiency of the proposed algorithm in improving the prediction performance and computational time compared with other nature‐inspired algorithms, which proves the ability of HHOA‐OBL in searching for the best hyperparameters values and selecting the most informative features for prediction tasks. Thus, the experiments and comparisons support the performance of the proposed approach in making predictions in other real applications.

show abstract

Section: The Proposed Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving Harris hawks optimization algorithm for hyperparameters estimation and feature selection in v‐support vector regression based on opposition‐based learning

Ismael

Qasim

Algamal

2020

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…On the other hand, smart computational techniques have emerged and evolved as powerful and advanced approaches that can resolve highly complex relatedmodeling topics (Amirian, Dejam, & Chen, 2018;Hemmati-Sarapardeh, Ghazanfari, Ayatollahi, & Masihi, 2016;Hemmati-Sarapardeh et al, 2018;Hobold & da Silva, 2019;Nait Amar & Zeraibi, 2018;Nait Amar, Zeraibi, & Redouane, 2018a;Nait Amar, Zeraibi, & Redouane, 2018b;Redouane, Zeraibi, & Amar, 2018;Shahsavar, Khanmohammadi, Karimipour, & Goodarzi, 2019;Xi, Gao, Xu, Zhao, & Li, 2018). Among the successful examples of soft computing techniques applications, we can cite production forcasting in thermal enhanced oil recovery (Amirian, Leung, Zanon, & Dzurman, 2015;Amirian, Fedutenko, Yang, Chen, & Nghiem, 2018), optimization of enhanced oil recovery techniques (Nait Amar & Zeraibi 2019), reservoir flood control (Chuntian & Chau, 2002), hydrology (Chau, 2017;Wu & Chau, 2011;Yaseen, Sulaiman, Deo, & Chau, 2019), and meteorology related topics (Ali Ghorbani, Kazempour, Chau, Shamshirband, & Ghazvinei, 2018;Moazenzadeh, Mohammadi, Shamshirband, & Chau, 2018).…”

Section: Modelmentioning

confidence: 99%

Modeling temperature dependency of oil - water relative permeability in thermal enhanced oil recovery processes using group method of data handling and gene expression programming

Menad

Zerhouni

Hemmati-Sarapardeh

et al. 2019

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

In the implementation of thermal enhanced oil recovery (TEOR) techniques, the temperature impact on relative permeability in oil-water systems (K rw and K ro ) is of special concern. Hence, developing a fast and reliable tool to model the temperature effect on K rw and K ro is still a major challenge for precise studying of TEOR processes. To reach the goal of this work, two promising soft-computing algorithms, namely Group Method of Data Handling (GMDH) and Gene Expression Programming (GEP) were employed to develop reliable and simple to use paradigms to predict the temperature dependency of K rw and K ro . To do so, a large database encompassing wide-ranging temperatures and fluids/rock parameters, was considered to establish these correlations. Statistical results and graphical analyses disclosed the high degree of accuracy for the proposed correlations in emulating the experimental results. In addition, GEP correlations were found to be the most consistent with root mean square error (RMSE) values of 0.0284 and 0.0636 for K rw and K ro , respectively. Lastly, the performance comparison against the preexisting correlations indicated the large superiority of the newly introduced correlations. The findings of this study can help for better understanding the temperature dependency of K rw and K ro in TEOR. ARTICLE HISTORY

show abstract

“…Its theory and method have been widely used to solve complex problems in engineering and scientific fields. Machine learning models such as artificial neural networks (ANN), decision trees, support vector machines, − and so on are widely employed in industry, which provide alternatives for HFT prediction. Especially, ANN have played a very important role in predicting hydrate formation. − However, it is easy to over fit and difficult to adjust the parameters; the training speed is slow, using ANN for external prediction is not a good choice.…”

Section: Introductionmentioning

confidence: 99%

Twin Support Vector Regression for Prediction of Natural Gas Hydrate Formation Conditions

2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Natural gas hydrates have become a threat to natural gas companies and oil industries for the formation of gas hydrates in transfer pipelines can lead to pipe blockage. Natural gas hydrate formation is favored by low temperature and high pressure; thus, if the right combination of temperature and pressure are well investigated, it is possible to solve the pipe blockage problems. Therefore, developing a precise, easy-to-use method to predict natural gas hydrate formation temperature (HFT) is very important. In this paper, we are intended to develop a novel machine learning model called twin support vector regression (TSVR) for predicting HFT in a wide range of natural gas mixtures. For constructing the TSVR model, 513 experimental data in the system methane, ethane, propane, butane, pentane, nitrogen, carbon dioxide/water, methane, carbon dioxide, propane, methanol, sodium chloride, and calcium chloride have been collected from open literature. We compared the performance of the TSVR model with least squares support vector regression (LSSVR) and three widely used correlations in the system methane, ethane, propane, butane, pentane, nitrogen, and carbon dioxide, which show that the TSVR model has fewer deviations than the LSSVR model and three correlations. The values of root-mean-square error (RMSE), mean absolute percentage error (MAPE), and correlation factor (R 2) are 2.4010, 0.0061, and 0.9108, respectively. In addition, statistical parameters show that the TSVR model can also surpass the LSSVR model in predicting HFT in the system water, methane, carbon dioxide, propane, methanol, sodium chloride, and calcium chloride.

show abstract

Application of hybrid support vector regression artificial bee colony for prediction of MMP in CO2-EOR process

Cited by 44 publications

References 53 publications

Improving Harris hawks optimization algorithm for hyperparameters estimation and feature selection in v‐support vector regression based on opposition‐based learning

Improving Harris hawks optimization algorithm for hyperparameters estimation and feature selection in v‐support vector regression based on opposition‐based learning

Modeling temperature dependency of oil - water relative permeability in thermal enhanced oil recovery processes using group method of data handling and gene expression programming

Twin Support Vector Regression for Prediction of Natural Gas Hydrate Formation Conditions

Contact Info

Product

Resources

About