Vol. 337 No. 8 (2026)
DOI https://doi.org/10.18799/24131830/2026/8/5657
Machine learning for reservoir potential assessment: a critical review of established and promising methods
Relevance. The oil and gas industry remains strategically important to the global economy, and the efficiency of field development is directly determined by the accuracy of reservoir potential assessment and geological system behavior prediction. However, reliable quantitative assessment of reservoir productivity is hampered by high geological heterogeneity, limited and diverse geological and production data, and the difficulty of integrating static and dynamic parameters. With the industry digitalization, machine learning methods are emerging as a promising tool capable of complementing or partially replacing classic hydrodynamic simulators by identifying complex nonlinear relationships between input geological characteristics and output development indicators. Aim. To critically systematize global experience in applying machine learning methods to assess reservoir potential and forecast oil and gas field development indicators. Methods. Analysis of scientific publications devoted to the application of machine learning methods, including neural networks, ensemble algorithms, probabilistic and hybrid models, to forecasting flow rates, cumulative production, and pressure. The characteristics of the input data used, approaches to model training, and metrics for assessing forecast quality are discussed. Results and conclusions. Machine learning methods have been shown to significantly accelerate reservoir potential assessment while maintaining accuracy comparable to hydrodynamic models. They effectively identify complex relationships between geological characteristics and dynamic system responses, making them a promising tool for the rapid analysis of development scenarios. However, key limitations remain sensitivity to the quality of input data and the limited nature of training samples. The authors note a trend toward hybrid approaches combining machine learning and physical and mathematical modeling, improving the robustness and interpretability of results. Despite the high level of automation, expert participation remains critical at the stages of data preparation, feature selection, and results interpretation.
For citation: Piskunov S.A., Truhachev M.S., Rukavishnikov V.S., Davoodi S. Machine learning for reservoir potential assessment: a critical review of established and promising methods. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2026, vol. 337, no. 8, pp. 168–183. http://doi.org/10.18799/24131830/2026/8/5657
Keywords:
reservoir potential, machine learning, production forecasting, deep learning, reservoir simulation, neural networks, surrogate models, recoverable reserves, reservoir productivity, hybrid models
References:
1. Halttunen K., Slade R., Staffell I. Evaluating the role of the oil and gas industry in energy transition in oil-producing countries: a systematic literature review. Energy Research & Social Science, 2025, vol. 120, 103905. DOI: 10.1016/j.erss.2023.103253.
2. Liang B., Liu J., You J., Jia J., Pan Y., Jeong H. Hydrocarbon production dynamics forecasting using machine learning: a state-of-the-art review. Fuel, 2023, vol. 337, 127067. DOI: 10.1016/j.fuel.2022.127067.
3. Normando M.N., Do Nascimento Junior D.R., De Souza A.C.B., Oliveira K.M.L., Nepomuceno Filho F., Da Silva Barbosa T.H., Salgueiro A.R.G., De Almeida N.M. A proposal for reservoir geostatistical modeling and uncertainty analysis of the Curima Field, Mundau Sub-Basin, Ceara Basin, Brazil. Journal of South American Earth Sciences, 2022, vol. 114, 103716. DOI: 10.1016/j.jsames.2022.103716.
4. Beavington-Penney S.J., Wright V.P., Barnett A., Kennedy S., Covill M. Integration of static and dynamic data and high-resolution sequence stratigraphy to define reservoir architecture and flow units within a "super giant" gas condensate and oil field, Kazakhstan. Marine and Petroleum Geology, 2019, vol. 101, pp. 486–501. DOI: 10.1016/j.marpetgeo.2018.11.005.
5. Subbey S., Christie M., Sambridge M. Prediction under uncertainty in reservoir modeling. Journal of Petroleum Science and Engineering, 2004, vol. 44, no. 1–2, pp. 143–153. DOI: 10.1016/j.petrol.2004.02.011.
6. Santos S.M.G., Gaspar A.T.F.S., Schiozer D.J. Managing reservoir uncertainty in petroleum field development: defining a flexible production strategy from a set of rigid candidate strategies. Journal of Petroleum Science and Engineering, 2018, vol. 171, pp. 516–528. DOI: 10.1016/j.petrol.2018.07.048.
7. Abbas A.E., Bakir N.O., Klutke G.A., Sun Z. Value of information in reservoir development projects: Technical indicators to prioritize uncertainties and information sources. Journal of Petroleum Science and Engineering, 2017, vol. 157, no. 3, pp. 1179–1191. DOI: 10.1016/j.petrol.2017.08.028.
8. Ng C.S.W., Nait Amar M., Jahanbani Ghahfarokhi A., Imsland L.S. A survey on the application of machine learning and metaheuristic algorithms for intelligent proxy modeling in reservoir simulation. Computers & Chemical Engineering, 2023, vol. 170, 108107. DOI: 10.1016/j.compchemeng.2022.108107.
9. Cao C., Jia P., Cheng L., Jin Q., Qi S. A review on application of data-driven models in hydrocarbon production forecast. Journal of Petroleum Science and Engineering, 2022, vol. 212, 110296. DOI: 10.1016/j.petrol.2022.110296.
10. Gu J., Liu W., Zhang K., Zhai L., Zhang Y., Chen F. Reservoir production optimization based on surrogate model and differential evolution algorithm. Journal of Petroleum Science and Engineering, 2021, vol. 205, 108879. DOI: 10.1016/j.petrol.2021.108879.
11. Fathy M., Kazemzadeh Haghighi F., Ahmadi M. Uncertainty quantification of reservoir performance using machine learning algorithms and structured expert judgment. Energy, 2024, vol. 288, 129906. DOI: 10.1016/j.energy.2023.129906.
12. Ahmed T. Reservoir engineering handbook. 5th ed. Oxford, Gulf Professional Publ., 2019. 492 p. DOI: 10.1016/C2016-0-04718-6.
13. He Y., Cheng S., Li L., Mu G., Zhang T., Xu H., Qin J., Yu H. From shallow to deep: the evolution of machine learning and mechanistic model integration in cancer research. Current Opinion in Systems Biology, 2025, vol. 40, 100541. DOI: 10.1016/J.COISB.2025.100541.
14. Guo Z., Reynolds A.C. Robust life-cycle production optimization with a support-vector-regression proxy. SPE Journal, 2018, vol. 23, no. 06, pp. 2409–2427. DOI: 10.2118/191378-PA.
15. Yahya W., Baolin Y., AlRassas A.M., Yuting W., Al-Khafaji H., Al Dawood R. Developing robust machine learning techniques to predict oil recovery: a comprehensive field and experimental study. Geoenergy Science and Engineering, 2025, vol. 250, 213853. DOI: 10.1016/j.geoen.2025.213853.
16. Abdullayeva F., Imamverdiyev Y. Development of oil production forecasting method based on deep learning. Statistics, Optimization & Information Computing, 2019, vol. 7, no. 4, pp. 826–839. DOI: 10.19139/soic-2310-5070-651.
17. Xia J.S., Khabaz M.K., Patra I., Khalid I., Alvarez J.R.N., Rahmanian A., Eftekhari S.A., Toghraie D. Using feed-forward perceptron Artificial Neural Network (ANN) model to determine the rolling force, power and slip of the tandem cold rolling. ISA Transactions, 2023, vol. 132, pp. 353–363. DOI: 10.1016/j.isatra.2022.06.009.
18. Sherstinsky A. Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network. Physica D: Nonlinear Phenomena, 2020, vol. 404, 132306. DOI: 10.1016/j.physd.2019.132306.
19. Foroud T., Seifi A., AminShahidi B. Assisted history matching using artificial neural network based global optimization method – applications to Brugge field and a fractured Iranian reservoir. Journal of Petroleum Science and Engineering, 2014, vol. 123, pp. 46–61. DOI: 10.1016/j.petrol.2014.07.034.
20. Zhang R., Hu J. Production performance forecasting method based on multivariate time series and vector autoregressive machine learning model for waterflooding reservoirs. Petroleum Exploration and Development, 2021, vol. 48, no. 1, pp. 201–211. DOI: 10.1016/S1876-3804(21)60016-2.
21. Machado T.J., Santos M.D., Oliveira G.P., Magalhães R.M. Cell-level deep learning as proxy model for reservoir simulation and production forecasting. Journal of Petroleum Exploration and Production Technology, 2025, vol. 15, art. 39. DOI: 10.1007/s13202-024-01889-2.
22. Du J., Zheng J., Liang Y., Ma Y., Wang B., Liao Q., Xu N., Ali A.M., Rashid M.I., Shahzad K. A deep learning-based approach for predicting oil production: a case study in the United States. Energy, 2024, vol. 288, 129688. DOI: 10.1016/j.energy.2023.129688.
23. Makarov N., Al-Shargabi M., Wood D.A., Burnaev E., Davoodi S. Prediction of oil production rate in multiple wells of a producing field applying combined deep-learning and optimization techniques. Fuel, 2026, vol. 406, 136847. DOI: 10.1016/j.fuel.2025.136847.
24. Li X., Xue C., Chen Y., Yuan F., Li Y., Zheng C., Zhang M., Ge C., Guo D., Lan X., Tang M., Lu S. 3D convolutional neural Network-based 3D mineral prospectivity modeling for targeting concealed mineralization within Chating area, middle-lower Yangtze River metallogenic Belt, China. Ore Geology Reviews, 2023, vol. 157, 105444. DOI: 10.1016/j.oregeorev.2023.105444.
25. Tang H., Fu P., Jo H., Jiang S., Sherman C.S., Hamon F., Azzolina N.A., Morris J.P. Deep learning-accelerated 3D carbon storage reservoir pressure forecasting based on data assimilation using surface displacement from InSAR. International Journal of Greenhouse Gas Control, 2022, vol. 120, 103765. DOI: 10.1016/j.ijggc.2022.103765.
26. Cui J.W., Sun W.Y., Jeong H., Liu J.R., Zhou W.X. Efficient deep-learning-based surrogate model for reservoir production optimization using transfer learning and multi-fidelity data. Petroleum Science, 2025, vol. 22, no. 4, pp. 1736–1756. DOI: 10.1016/j.petsci.2025.02.014.
27. Li Y., Jia D., Wang S., Qu R., Qiao M., Liu H. Surrogate model for reservoir performance prediction with time-varying well control based on depth generative network. Petroleum Exploration and Development, 2024, vol. 51, no. 5, pp. 1287–1300. DOI: 10.1016/S1876-3804(25)60541-6.
28. Zang J., Wang J., Zhang K., El-Alfy E.S.M., Mandziuk J. Expertise-informed Bayesian convolutional neural network for oil production forecasting. Geoenergy Science and Engineering, 2024, vol. 240, 213061. DOI: 10.1016/j.geoen.2024.213061.
29. Kim J., Lee K., Choe J. Efficient and robust optimization for well patterns using a PSO algorithm with a CNN-based proxy model. Journal of Petroleum Science and Engineering, 2021, vol. 207, 109088. DOI: 10.1016/j.petrol.2021.109088.
30. Joshi R. Applied graph data science. 1st ed. Amsterdam, Elsevier, 2025. 314 p. DOI: 10.1016/B978-0-443-29654-3.00017-X.
31. Wu T., Wang Q., Zhang Y., Ying R., Cao K., Sosič R., Jalali R., Hamam H., Maucec M., Leskovec J. Learning large-scale subsurface simulations with a hybrid graph network simulator. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD ’22). Washington, DC, USA, August 14–18, 2022. New York, ACM, 2022. pp. 4184–4194. DOI: 10.1145/3534678.3539045.
32. Tang H., Durlofsky L.J. Graph network surrogate model for subsurface flow optimization. Journal of Computational Physics, 2024, vol. 512, 113132. DOI: 10.1016/j.jcp.2024.113132.
33. Ma X., Zhao J., Zhou D., Zhang K., Tian Y. Deep graph learning-based surrogate model for inverse modeling of fractured reservoirs. Mathematics, 2024, vol. 12, no. 5, 754. DOI: 10.3390/MATH12050754.
34. Huang Z.Q., Wang Z.X., Hu H.F., Zhang S.M., Liang Y.X., Guo Q., Yao J. Dynamic interwell connectivity analysis of multi-layer waterflooding reservoirs based on an improved graph neural network. Petroleum Science, 2024, vol. 21, no. 2, pp. 1062–1080. DOI: 10.1016/j.petsci.2023.11.008.
35. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser L., Polosukhin I. Attention is all you need. arXiv preprint arXiv:1706.03762, 2017.
36. Ma S., Zhang T., Wang H., Wang H., Li N., Zhu H., Zhu J., Wang J. Transformer-based forecasting for high-frequency natural gas production data. Energy AI, 2025, vol. 21, 100535. DOI: 10.1016/j.egyai.2025.100535.
37. Fragalla M.A.M., Yan W., Deng J., Xue L., Hegair F., Zhang W., Li G. Time series production forecasting of natural gas based on transformer neural networks. Geoenergy Science and Engineering, 2025, vol. 248, 213749. DOI: 10.1016/j.geoen.2025.213749.
38. Deng W., Xin X., Song R., Yang X., Wang W., Yu G. A time series forecasting method for oil production based on Informer optimized by Bayesian optimization and the hyperband algorithm (BOHB). Computers & Chemical Engineering, 2025, vol. 197, 109068. DOI: 10.1016/j.compchemeng.2025.109068.
39. Ahmad H. Zafar, Zafar A., Sadiq M.N., Awasthi A.K., Emadifar H., Ahmed K.K. Evolution of physics-informed neural networks: recent architectural variants and optimization strategies. Array, 2026, vol. 29, 100688. DOI: 10.1016/j.array.2026.100688.
40. Han J.X., Xue L., Wei Y.S., Qi Y.D., Wang J.L., Liu Y.T., Zhang Y.Q. Physics-informed neural network-based petroleum reservoir simulation with sparse data using domain decomposition. Petroleum Science, 2023, vol. 20, no. 6, pp. 3450–3460. DOI: 10.1016/j.petsci.2023.10.019.
41. Chen H.Y., Xue L., Liu L., Zou G.F., Han J.X., Dong Y.B., Cong M.Z., Liu Y.T., Hosseini-Nasab S.M. Physics-informed graph neural network for predicting fluid flow in porous media. Petroleum Science, 2025, vol. 22, no. 10, pp. 4240–4253. DOI: 10.1016/j.petsci.2025.06.007.
