Prediction of Reservoir Flow Capacity in Sandstone Formations: A Comparative Analysis of Machine Learning Models
Article Sidebar
Main Article Content
Abstract
Sand production is one of the major challenges in the oil and gas industry, impacting the operational integrity and economic efficiency of oil extraction activities. This study focuses on predicting Reservoir Flow Capacity (RFC) in sandstone formations by analyzing geological and petrophysical properties critical to reservoir performance and mechanical stability. It also identified key factors that impact the mechanical stability of formations during production. Given a large number of input variables that enclose geological and environmental factors, the study set the correlation of these conditions to provide profound analysis and reveal profound patterns within the data. With the following supervised machine learning algorithms: Random Forest, Artificial Neural Network (ANN) and Support Vector Regression (SVR); the study modeled RFC. The algorithms were selected for their ability to model complex relationships in reservoir characterization, with Random Forest excelling in high-dimensional data handling, ANN in pattern learning, and SVR in regression-based predictions. Model evaluation using R-Squared metrics showed that the Random Forest model possesses a good level of accuracy of 0.9573 in predicting the RFC, compared to the ANN and SVR model which had R-Squared values of 0.9390 and 0.7294 respectively. The SVR model had large variations from the actual values and hence was not very useful for our predictions. Further analysis using the developed machine learning models revealed that geological formation thickness, reservoir thickness, and permeability are the most critical parameters influencing reservoir flow capacity and overall rock stability.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Halsey, T., Agrawal, G., Bailey, J. R., Balhoff, M., Borglum, S. J., Mohanty, K. K., & Traver, M., (2023). Grand challenges for the oil and gas industry for the next decade and beyond. Journal of Petroleum Technology.
Ayal, A., & Sadeq, D. (2024). Sand production prediction and management using a one-dimensional geomechanical model: A case study in NahrUmr Formation, Subba Oil Field. Iraqi Geological Journal, 57(2C), 64–83. https://doi.org/10.46717/igj.57.2C.6ms-2024-9-14
Laoufi, H., Megherbi, Z., Zeraibi, N., Merzoug, A., & Ladmia, A. (2022). Selection of sand control completion techniques using machine learning. International Geomechanics Symposium. https://doi.org/10.56952/IGS-2022-118
Chen, X., Zhang, J., Wang, Y., Liu, H., Li, Q., & Wu, Y. (2024). A real-time drilling parameters optimization method for offshore large-scale cluster extended reach drilling based on intelligent optimization algorithm and machine learning. Ocean Engineering, 291, 116375. https://doi.org/10.1016/j.oceaneng.2023.116375
Arab Oil & Natural Gas. (2017). Sand control - AONG. https://www.arab-oil-naturalgas.com/sand-control/
Saghandali, F., Salehi, M., Hosseinzadehsemnani, R., Moghanloo, R. G., & Taghikhani, V. (2022). A review on chemical sand production control techniques in oil reservoirs. Energy & Fuels, 36(10), 5185-5208. https://doi.org/10.1021/acs.energyfuels.2c00700
Kazidenov, D., Omirbekov, S., Zhanabayeva, M., & Amanbek, Y. (2025). Experimental and numerical study of the effect of polymer flooding on sand production in poorly consolidated porous media. Geoenergy Science and Engineering, 249, 213746. https://doi.org/10.1016/j.geoen.2025.213746
Muñoz‐Ibáñez, A., Herbón‐Penabad, M., Li, Y., & Delgado‐Martín, J. (2025). Impact of fluids on the Mode I fracture toughness of two granites and one sandstone. Journal of Geophysical Research: Solid Earth, 130(1), e2024JB030441. https://doi.org/10.1029/2024JB030441
Asfha, D. T., Abubakar, A. I., Ahmed, M. A., Shariff, A. M., & Kamel, A. R. (2024). Mechanisms of sand production, prediction–a review and the potential for fiber optic technology and machine learning in monitoring. Journal of Petroleum Exploration and Production Technology, 14(10), 2577–2616. https://doi.org/10.1007/s13202-024-01860-1
Cheddad, F. A. (2023). Enhancing petrophysical studies with machine learning: A field case study on permeability prediction in heterogeneous reservoirs. arXiv. https://doi.org/10.48550/ARXIV.2305.07145
Krishna, S., Irfan, S. A., Keshavarz, S., Thonhauser, G., & Ilyas, S. U. (2024). Smart predictions of petrophysical formation pore pressure via robust data-driven intelligent models. Multiscale and Multidisciplinary Modeling, Experiments and Design, 7(6), 5611–5630. https://doi.org/10.1007/s41939-024-00542-z
Ali, M., Zhu, P., Jiang, R., Huolin, M., Ehsan, M., Hussain, W., Zhang, H., Ashraf, U. & Ullah, J. (2023). Reservoir characterization through comprehensive modeling of elastic logs prediction in heterogeneous rocks using unsupervised clustering and class-based ensemble machine learning. Applied Soft Computing, 148, 110843. https://doi.org/10.1016/j.asoc.2023.110843
Otmane, M., Imtiaz, S., Jaluta, A. M., & Aborig, A. (2025). Boosting reservoir prediction accuracy: A hybrid methodology combining traditional reservoir simulation and modern machine learning approaches. Energies, 18(3), 657. https://doi.org/10.3390/en18030657
Jordan, T. E. (2016). Appalachian Basin play fairway analysis: Natural sedimentary reservoirs data 2016 revision [data set]. DOE Geothermal Data Repository; Cornell University. https://doi.org/10.15121/1495428
Raheem, E. (2024). Missing data imputation: A practical guide. In A. K. Mitra (Ed.), Statistical Approaches for Epidemiology: From Concept to Application (293–316). Springer International Publishing. https://doi.org/10.1007/978-3-031-41784-9_18
Min, C., Wen, G., Gou, L., Li, X. & Yang, Z. (2022). Interpretability and causal discovery of the machine learning models to predict the production of CBM wells after hydraulic fracturing. arXiv. https://doi.org/10.48550/ARXIV.2212.10718
Feng, P., Wang, R., Sun, J., Yan, W., Chi, P., & Luo, X. (2024). An interpretable ensemble machine-learning workflow for permeability predictions in tight sandstone reservoirs using logging data. Geophysics, 89(5), MR265–MR280. https://doi.org/10.1190/geo2023-0657.1
Onciul, R., Tataru, C.-I., Dumitru, A. V., Crivoi, C., Serban, M., Covache-Busuioc, R.-A., Radoi, M. P., & Toader, C. (2025). Artificial intelligence and neuroscience: Transformative synergies in brain research and clinical applications. Journal of Clinical Medicine, 14(2), 550. https://doi.org/10.3390/jcm14020550
Putra, D. S., Azmi, M., Muslikhin, & Purwanto, W. (2022). ANN activation function comparative study for sinusoidal data. Journal of Physics: Conference Series, 2406(1), 012029. https://doi.org/10.1088/1742-6596/2406/1/012029
Saha, N., Swetapadma, A., & Mondal, M. (2023). A brief review on artificial neural network: Network structures and applications. In 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS) (1974–1979). IEEE. https://doi.org/10.1109/ICACCS57279.2023.10112753
Salman, H. A., Kalakech, A., & Steiti, A. (2024). Random forest algorithm overview. Babylon Journal of Machine Learning, 2024, 69–79. https://doi.org/10.58496/BJML/2024/007
Becker, T., Rousseau, A.-J., Geubbelmans, M., Burzykowski, T., & Valkenborg, D. (2023). Decision trees and random forests. American Journal of Orthodontics and Dentofacial Orthopedics, 164(6), 894–897. https://doi.org/10.1016/j.ajodo.2023.09.011
Osahon, U., & Efetobore, G. M. (2023). Reservoir characterization: Enhancing accuracy through advanced rock physics techniques. Journal of Geosciences and Geomatics, 11(2), 67–78. https://doi.org/10.12691/jgg-11-2-4
Solanke, B., Onita, F. M., Ochulor, O. J., & Iriogbe, H. O. (2024). Techniques for improved reservoir characterization using advanced geological modeling in the oil and gas industry. International Journal of Applied Research in Social Sciences, 6(9), 2060–2088. https://doi.org/10.51594/ijarss.v6i9.1542