ENSEMBLE NEURAL NETWORK APPROACH FOR PREDICTING WATER SATURATION USING WELL LOGS
DOI:
https://doi.org/10.60787/jnamp.vol73no.754Keywords:
Water saturation, ensemble model, neural network, well log, MATLAB, core data, learning, reservoirAbstract
Accurate estimation of water saturation (????????) is vital for hydrocarbon recovery from a reservoir. Empirical equations (EE) such as: Archie, Simandoux, Waxman-Smith and Dual water model are used to estimate water saturation. The results are unreliable and strongly depend on costly and time-consuming core analysis. This study presents ensemble neural network approach for predicting water saturation using well logs. The results predicted by the ensemble model in MATLAB was evaluated against (i) core data (ii) empirically derived data (iii) single expert network model, using standard performance metrics such as MSE, coefficient of determination (R²) and coefficient of regression (R). The results show that the ensemble approach significantly improves prediction accuracy because it closely fits the core data.
Downloads
References
Ezekwe, Nnaemeka, (2011) “Petroleum reservoir engineering practice”, Pearson Education, Inc.
Nabil Al-Bulushi, Peter R. King, Martin J. Blunt and Martin Kraaijveld (2009), “Development of
Artificial Neural Network Models for Predicting Water Saturation and Fluid Distribution” Journal of
Petroleum Science and Engineering, vol 68, 197–208
Ahmed Farid Ibrahim, Salaheldin Elkatatny and Mustafa Al Ramadan (2022), “Prediction of Water
Saturation in Tight Gas Sandstone Formation Using Artificial Intelligence” American Chemical Society,
(ACS Omega) 7, 215−222
Onwusinkwue S., Azi S, Onwusinkwue N, and Ojo K. (2025), “Predicting Permeability Of
Reservoir using Committee Neural Network”, Transaction of National Association of Mathematical
Physics, 22, (125-134)
Okon, A. N., Adewole, S. E., and Uguma, E. M. (2021). “Artificial neural network model for reservoir
petrophysical properties: Porosity, permeability and water saturation prediction” Model. Earth Syst.
Environ. 7 (4), 2373–2390. http://doi:10.1007/s40808-020-01012-4
Soleimani F., Hosseini E and Hajivand F. (2020). “Estimation of reservoir Porosity using analysis
of eismic attributes in an Iranian oil field” J.Pet.Explor. Prod.Technol. 10(4), 1289–1316.
doi:10.1007/s13202-020-00833-4
Haykin S. (2009), “Neural networks and learning machines” 3rd edition, Pearson Education, Inc.,
Upper Saddle River, New Jersey 07458.
Wood DA (2019), “Predicting Porosity, Permeability and Water Saturation Applying An Optimized
Nearest Neighbour, Machine-Learning and Data-Mining Network Of Well-Log Data”. J Pet Sci Eng
https://doi.org/10.1016/j.petrol.2019.106587 Engineering 205, 108869
Rostamian, A., Heidaryan, E., Ostadhassan, M., (2022) “Evaluation of Different Machine Learning
Frameworks to Predict CNL-FDC-PEF Logs Via Hyperparameters Optimization and Feature
Selection” J. Petrol. Sci. Eng. 208, 109463.
Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al Dujaili, Ye Duan, Omran Al,
Shamma, J. Santamaría, Mohammed A. Fadhel, Muthana, Amid and Laith Farhan (2021) “Review of
deep learning: concepts, CNN architectures, challenges, applications, future directions, Big Data “2021)
:53 https://doi.org/10.1186/s40537-021-00444-8
Alpana Bhatt (2002) “Reservoir properties from well logs using neural networks” Ph.D Thesis,
Department of Petroleum Engineering and Applied Geophysics, Norwegian University of Science and
Technology
Ahmadi, M. A., and Chen, Z., (2019). “Comparison of Machine Learning Methods for Estimating
Permeability and Porosity Of Oil Reservoirs Via Petrophysical Logs”. Petroleum Journal 5, 271–284.
doi:10.1016/j.petlm.2018.06.002
Sun K and Dong L (2022) “A New Development Algorithm for Permeability Prediction: A New
Milestone”. Front. Ecol. Evol. 10:1066800. doi: 10.3389/fevo.2022.1066800
Sambo C, Hermana M, Babasafari A, and Janjuhah H. T (2018), “Application of Artificial Intelligent
Methods for Predicting Water Saturation From New Seismic Attributes”. In: Paper SPE OTC-28221
presented at the offshore technology conference Asia, Kuala Lum- pur, Malaysia, 20–23 Mar.
https://doi.org/10.2118/28221-MS
Wood DA (2019), “Predicting porosity, permeability and water saturation applying an optimized
Nearest neighbour, machine-learning and data-mining network of well-log data. J Pet Sci Eng
:1–17. https://doi.org/10.1016/j.petrol.2019.106587 Engineering 205, 108869
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Journals of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
