PREDICTING PERMEABILITY OF RESERVOIR USING COMMITTEE NEURAL NETWORK
DOI:
https://doi.org/10.60787/tnamp.v22.549Keywords:
Permeability, Neural network, Committee neural network, Reservoir characterization MATLABAbstract
Permeability is an essential petro-physical property required to efficiently characterize a reservoir. Since it is a complex function of several interrelated factors such as lithology, pore fluid composition and porosity; it varies significantly within the formation. The routine and economic procedure in the oil industry has been to estimate it from well logs using empirical equations (EE). Artificial neural networks have emerged as a data driven tool that has ability to map complex statistical relationship between data; such as relation between welllog and reservoir properties. In this study, seven (7) multiple-layer perceptron (MLP) networks were trained using well logs as input data and core data as output data in MATLAB neural network toolbox. The best four (4) MLPs, called expert networks (EN), were selected and combined to form committee network (CN). The committee network fused knowledge by combining the individual outputs of the experts to arrive at a better overall output. Since core data gives the best permeability, the correlation coefficients obtained between core data and the respective CN, EN and EE methods was 0.89: 0.71: 0.61. Clearly, the correlation values for CN and EN gives a better prediction of the core permeability compared to EE.
Downloads
References
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 (PhD thesis)
Saikia, P., Baruah, R.D., Singh, S.K., Chaudhuri, P.K., (2019) “Artificial Neural Networks in the domain of reservoir characterization: A review from shallow to deep models” Computers and Geosciences (2019), https://doi.org/10.1016/j.cageo.2019.104357
Xingye Liu , Qiang Ge, Xiaohong Chen, Jingye Li, Yangkang Chen, (2021) “Extreme learning machine for multivariate reservoir characterization” Journal of Petroleum Science and Engineering 205, 108869
Laith Alzubaidi, Jinglan Zhang, Amjad J. Humaidi, Ayad Al Dujaili, Ye Duan, Omran AlShamma, J. Santamaría, Mohammed A. Fadhel, Muthana, Amid and Laith Farhan (2021) “Review of deep learning: concepts, CNN architectures, challenges, applications, future directions” J Big Data, 2021, 8:53, https://doi.org/10.1186/s40537-021-00444-8
Haykin S. (2009) “Neural networks and learning machines”, 3rd edition, Pearson Education, Inc.,Upper Saddle River, New Jersey 07458.
Jain A., (1996) “Artificial Neural Network-a tutorial” IEEE volume 0018, 9162 page 31-43
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.
Wen Pan; Carlos Torres-Verdín; Ian J. Duncan; Michael J. Pyrcz (2023) “Improving multiwall petrophysical interpretation from well logs via machine learning and statistical models” Geophysics 88 (2): pg 159–175. https://doi.org/10.1190/geo2022-0151.1
Tom I. U, Okon A. N, Okologume W. C (2020) “Volumetric approach based DOE and ANN models for estimating reservoirs oil in place” Int J Sci Eng Res 11(7):873–88
Soleimani F., Hosseini E and Hajivand F. (2020). “Estimation of reservoir Porosity using analysis of seismic attributes in an Iranian oil field” J.Pet.Explor. Prod.Technol. 10(4), 1289–1316. doi:10.1007/s13202-020-00833-4
Abdulhamit Subasi, Mohamed F. El-Amin, Tarek Darwich and Mubarak Dossary (2022) “Permeability prediction of petroleum reservoirs using stochastic gradient boosting regression” Journal of Ambient Intelligence and Humanized Computing volume 13, 3555–3564 (2022). https://doi.org/10.1007/s12652-020-01986-0
R. Gholami, A. R. Shahraki, M. Jamali Paghaleh, (2012) "Prediction of Hydrocarbon Reservoirs Permeability Using Support Vector Machine", Mathematical Problems in Engineering, vol. 2012, Article ID 670723, 18 pages, https://doi.org/10.1155/2012/670723
Sambo CH, Hermana M, Babasari A, Janjuhah HT, Ghosh DP (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
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
Bagheripour P. (2014) “Committee neural network model for rock permeability prediction” Journal of Applied Geophysics, Volume 104, May 2014, Pages 142-148https://doi.org/10.1016/j.jappgeo.2014.03.001
Ezekwe, Nnaemeka, (2011): Petroleum reservoir engineering practice, Pearson Education, Inc.
MATLAB, 2014B “Neural network Toolbox” The MathWorks, Inc. https://www.mathworks.com/products/neural-network.html
Bishop C. M., (1994) “Neural network and their application” rev. scim instrum, America Institute of Physics, volume 65, No:6 page 1803-1832 (0034-6748)
Chang-Hsu Chen and Zsay-Shing Lin (2006), “A committee machine with empirical formulas for permeability prediction” Computers & Geosciences 32 (2006) 485–496
Downloads
Published
Issue
Section
License
Copyright (c) 2025 The Transactions of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
