Kinematic Viscosity of Petroleumat at 37.78 ℃: A Comprehensive Comparison of Machine Learning Techniques

Youssef Kassem; Huseyin Camur; Almonsef Alhadi Salem Mosbah

doi:10.48084/etasr.10770

Authors

Youssef Kassem Department of Mechanical Engineering, Near East University, Nicosia, Cyprus | Energy Environment and Water Research Center, Near East University, Nicosia, Cyprus
Huseyin Camur Department of Mechanical Engineering, Near East University, Nicosia, Cyprus
Almonsef Alhadi Salem Mosbah High and Intermediate Institute of Agricultural Technology, Gheran, Libya

Volume: 15 | Issue: 4 | Pages: 26027-26037 | August 2025 | https://doi.org/10.48084/etasr.10770

Received: 2 March 2025 | Revised: 26 March 2025 | Accepted: 9 April 2025 | Online: 2 August 2025

Corresponding author: Youssef Kassem

Abstract

The viscosity of crude oil is a significant component influencing oil recovery and flow behavior, yet accurately predicting viscosity remains a significant challenge in reservoir optimization, requiring the use of predictive models. This study evaluates eight Artificial Intelligence (AI) models, Feed-forward Neural Network (FFNN), Cascade Forward Neural Network (CFNN), Elman Neural Network (ENN), Multi-layer Perceptron Neural Network (MLPNN), Radial Basis Function Neural Network (RBFNN), k-Nearest Neighbor (kNN), Support Vector Regression (SVR), and Extreme Learning Machine (ELM), as well as three mathematical models, Poisson Regression Model (PRM), Quadratic Model (QM), and Multiple Linear Regression (MLR), for predicting the Kinematic Viscosity (KV) of crude oil at 37.78 ℃. A dataset of 274 crude oil samples was compiled from literature sources, including Molecular Weight (MW), Refractive Index (RI), Sulfur content (S),Specific Gravity (SG), and Initial Boiling Points (IBP)ranging from 70℃ to 565℃. To identify the most influential factors affecting KV, Principal Component Analysis (PCA), Pearson's Correlation Coefficient (PCC), and Decision Trees (DT)were applied, highlightingIBP-280 ℃, IBP-343 ℃, S, RI, MW, and SG as key variables. Subsequently, 63 MLPNN models were trained with various input combinations to evaluate their impact on prediction accuracy. Four models, M#1 [SG, MW], M#2 [SG, IBP-280 ℃, IBP-343 ℃], M#3 [SG, S, IBP-280 ℃, IBP-343 ℃], and M#4 [SG, IBP-280 ℃, IBP-343 ℃, RI, MW], demonstrated superior performance based on multiple statistical metrics. These four feature sets were then incorporated into the AI and mathematical models for further evaluation. Comparative analysis revealed that ELM, RBFNN, and PRM models exhibited the highest accuracy and stability among individual approaches. To further enhance prediction quality, a hybrid ensemble model (RBFNN-ELM-PRM) was developed, integrating the strengths of these three models. The ensemble, using the feature set [SG, IBP-280℃, IBP-343℃, RI, MW], outperformed all individual models, offering improved robustness and precision in KV prediction.

Keywords:

crude oil, kinematic viscosity, AI, feature selection, hybrid model

Downloads

Download data is not yet available.

References

P. E. Oguntunde, O. O. Ojo, O. A. Oguntunde, and H. I. Okagbue, "Crude Oil Importation and Exportation in Nigeria: An Exploratory and Comparative Study,"Engineering, Technology & Applied Science Research, vol. 8, no. 5, pp. 3329–3331, Oct. 2018. DOI: https://doi.org/10.48084/etasr.2172

H. Luo, J. Wen, C. Lv, and Z. Wang, "Modeling of viscosity of unstable crude oil–water mixture by characterization of energy consumption and crude oil physical properties,"Journal of Petroleum Science and Engineering, vol. 212, May 2022, Art. no. 110222. DOI: https://doi.org/10.1016/j.petrol.2022.110222

M. A. Al-Marhoun, S. Nizamuddin, A. A. A. Raheem, S. S. Ali, and A. A. Muhammadain, "Prediction of crude oil viscosity curve using artificial intelligence techniques,"Journal of Petroleum Science and Engineering, vol. 86–87, pp. 111–117, May 2012. DOI: https://doi.org/10.1016/j.petrol.2012.03.029

I. V. Derevich and R. S. Gromadskaya, "Effect of Dissolved Gases on the Viscosity of Petroleum,"Theoretical Foundations of Chemical Engineering, vol. 36, no. 6, pp. 583–588, Nov. 2002. DOI: https://doi.org/10.1023/A:1021217901966

A. J. Rowane et al., "Effect of Composition, Temperature, and Pressure on the Viscosities and Densities of Three Diesel Fuels,"Journal of Chemical & Engineering Data, vol. 64, no. 12, pp. 5529–5547, Dec. 2019. DOI: https://doi.org/10.1021/acs.jced.9b00652

E. Bahonar, M. Chahardowli, Y. Ghalenoei, and M. Simjoo, "New correlations to predict oil viscosity using data mining techniques,"Journal of Petroleum Science and Engineering, vol. 208, Jan. 2022, Art. no. 109736. DOI: https://doi.org/10.1016/j.petrol.2021.109736

S. Lv et al., "Viscosity Reduction of Heavy Oil by Ultrasonic,"Petroleum Chemistry, vol. 60, no. 9, pp. 998–1002, Sep. 2020. DOI: https://doi.org/10.1134/S0965544120090194

G. Centeno, G. Sánchez-Reyna, J. Ancheyta, J. A. D. Muñoz, and N. Cardona, "Testing various mixing rules for calculation of viscosity of petroleum blends,"Fuel, vol. 90, no. 12, pp. 3561–3570, Dec. 2011. DOI: https://doi.org/10.1016/j.fuel.2011.02.028

X. Gao, P. Dong, J. Cui, and Q. Gao, "Prediction Model for the Viscosity of Heavy Oil Diluted with Light Oil Using Machine Learning Techniques,"Energies, vol. 15, no. 6, Mar. 2022, Art. no. 2297. DOI: https://doi.org/10.3390/en15062297

D. Stratiev et al., "Petroleum viscosity modeling using least squares and ANN methods,"Journal of Petroleum Science and Engineering, vol. 212, May 2022, Art. no. 110306. DOI: https://doi.org/10.1016/j.petrol.2022.110306

D. Stratiev et al., "Prediction of petroleum viscosity from molecular weight and density,"Fuel, vol. 331, Jan. 2023, Art. no. 125679. DOI: https://doi.org/10.1016/j.fuel.2022.125679

M. Sadi and A. Shahrabadi, "Experimental Measurement and Accurate Prediction of Crude Oil Viscosity Utilizing Advanced Intelligent Approaches,"Natural Resources Research, vol. 32, no. 4, pp. 1657–1682, Aug. 2023. DOI: https://doi.org/10.1007/s11053-023-10204-5

F. Torabi, A. Abedini, and R. Abedini, "The Development of an Artificial Neural Network Model for Prediction of Crude Oil Viscosities,"Petroleum Science and Technology, vol. 29, no. 8, pp. 804–816, Feb. 2011. DOI: https://doi.org/10.1080/10916460903485876

A. Naseri, M. Nikazar, and S. A. Mousavi Dehghani, "A correlation approach for prediction of crude oil viscosities,"Journal of Petroleum Science and Engineering, vol. 47, no. 3–4, pp. 163–174, Jun. 2005. DOI: https://doi.org/10.1016/j.petrol.2005.03.008

B. Ghorbani, M. Ziabasharhagh, and M. Amidpour, "A hybrid artificial neural network and genetic algorithm for predicting viscosity of Iranian crude oils,"Journal of Natural Gas Science and Engineering, vol. 18, pp. 312–323, May 2014. DOI: https://doi.org/10.1016/j.jngse.2014.03.011

M. H. Rammay and A. Abdulraheem, "PVT correlations for Pakistani crude oils using artificial neural network,"Journal of Petroleum Exploration and Production Technology, vol. 7, no. 1, pp. 217–233, Mar. 2017. DOI: https://doi.org/10.1007/s13202-016-0232-z

M. A. Oloso, M. G. Hassan, M. B. Bader-El-Den, and J. M. Buick, "Ensemble SVM for characterisation of crude oil viscosity,"Journal of Petroleum Exploration and Production Technology, vol. 8, no. 2, pp. 531–546, Jun. 2018. DOI: https://doi.org/10.1007/s13202-017-0355-x

M. Razghandi, A. Hemmati-Sarapardeh, F. Rashidi, B. Dabir, and S. Shamshirband, "Smart models for predicting under-saturated crude oil viscosity: a comparative study,"Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, vol. 41, no. 19, pp. 2326–2333, Oct. 2019. DOI: https://doi.org/10.1080/15567036.2018.1555634

M. Talebkeikhah et al., "Experimental measurement and compositional modeling of crude oil viscosity at reservoir conditions,"Journal of the Taiwan Institute of Chemical Engineers, vol. 109, pp. 35–50, Apr. 2020. DOI: https://doi.org/10.1016/j.jtice.2020.03.001

M. R. Mahdiani, E. Khamehchi, S. Hajirezaie, and A. Hemmati-Sarapardeh, "Modeling viscosity of crude oil using k-nearest neighbor algorithm,"Advances in Geo-Energy Research, vol. 4, no. 4, pp. 435–447, Dec. 2020. DOI: https://doi.org/10.46690/ager.2020.04.08

E. Khamehchi, M. R. Mahdiani, M. A. Amooie, and A. Hemmati-Sarapardeh, "Modeling viscosity of light and intermediate dead oil systems using advanced computational frameworks and artificial neural networks,"Journal of Petroleum Science and Engineering, vol. 193, Oct. 2020, Art. no. 107388. DOI: https://doi.org/10.1016/j.petrol.2020.107388

U. Sinha, B. Dindoruk, and M. Soliman, "Machine learning augmented dead oil viscosity model for all oil types,"Journal of Petroleum Science and Engineering, vol. 195, Dec. 2020, Art. no. 107603. DOI: https://doi.org/10.1016/j.petrol.2020.107603

F. Hadavimoghaddam et al., "Prediction of Dead Oil Viscosity: Machine Learning vs. Classical Correlations,"Energies, vol. 14, no. 4, Feb. 2021, Art. no. 930. DOI: https://doi.org/10.3390/en14040930

R. E. Nogales and M. E. Benalcázar, "Analysis and Evaluation of Feature Selection and Feature Extraction Methods,"International Journal of Computational Intelligence Systems, vol. 16, no. 1, Sep. 2023, Art. no. 153. DOI: https://doi.org/10.1007/s44196-023-00319-1

A. Shafiei, A. Tatar, M. Rayhani, M. Kairat, and I. Askarova, "Artificial neural network, support vector machine, decision tree, random forest, and committee machine intelligent system help to improve performance prediction of low salinity water injection in carbonate oil reservoirs,"Journal of Petroleum Science and Engineering, vol. 219, Dec. 2022, Art. no. 111046. DOI: https://doi.org/10.1016/j.petrol.2022.111046

Y. Kassem, I. M. Kareem, H. M. Nazif, A. M. Ahmed, and H. I. Ahmed, "Predicting groundwater drawdown in Zakho region, Northern Iraq, using machine learning models optimized by the whale optimization algorithm,"Environmental Earth Sciences, vol. 83, no. 22, Nov. 2024, Art. no. 642. DOI: https://doi.org/10.1007/s12665-024-11923-5

H. Gökçekuş, Y. Kassem, and J. Aljamal, "Analysis of different combinations of meteorological parameters in predicting rainfall with an ANN approach: a case study in Morphou, Northern Cyprus,"Desalination and Water Treatment, vol. 177, pp. 350–362, Feb. 2020. DOI: https://doi.org/10.5004/dwt.2020.24988

Y. Kassem, "Analysis of different combinations of meteorological parameters and well characteristics in predicting the groundwater chloride concentration with different empirical approaches: a case study in Gaza Strip, Palestine,"Environmental Earth Sciences, vol. 82, no. 6, Mar. 2023, Art. no. 134. DOI: https://doi.org/10.1007/s12665-023-10767-9

J. Anmala and V. Turuganti, "Comparison of the performance of decision tree (DT) algorithms and extreme learning machine (ELM) model in the prediction of water quality of the Upper Green River watershed,"Water Environment Research, vol. 93, no. 11, pp. 2360–2373, Nov. 2021. DOI: https://doi.org/10.1002/wer.1642

V. Nourani, P. Asghari, and E. Sharghi, "Artificial intelligence based ensemble modeling of wastewater treatment plant using jittered data,"Journal of Cleaner Production, vol. 291, Apr. 2021, Art. no. 125772. DOI: https://doi.org/10.1016/j.jclepro.2020.125772

G. P. Zhang, "A neural network ensemble method with jittered training data for time series forecasting,"Information Sciences, vol. 177, no. 23, pp. 5329–5346, Dec. 2007. DOI: https://doi.org/10.1016/j.ins.2007.06.015

P. Kazienko, E. Lughofer and B. Trawiński, "Hybrid and Ensemble Methods in Machine Learning,"Journal of Universal Computer Science, vol. 19, no. 4, pp. 457-461, Feb. 2013.

A. Hemmati‐Sarapardeh, M. Ghazanfari, S. Ayatollahi, and M. Masihi, "Accurate determination of the CO2‐crude oil minimum miscibility pressure of pure and impure CO2 streams: A robust modelling approach,"The Canadian Journal of Chemical Engineering, vol. 94, no. 2, pp. 253–261, Feb. 2016. DOI: https://doi.org/10.1002/cjce.22387