Vol. 337 No. 2 (2026)
DOI https://doi.org/10.18799/24131830/2026/2/5002
Machine learning for sedimentological and facies reconstructions of hydrocarbon reservoirs: a critical review of deployed and emerging methods
Relevance. The predictive power of a geological model directly determines the efficiency and economic viability of oil and gas field development. However, reconstructing the accurate spatial structure of reservoirs is hindered by the scarcity of core data, uneven well data density, and heterogeneity of geological and geophysical information. Under conditions of digital transformation in the oil and gas industry, machine learning methods are increasingly being integrated into geological modeling, complementing and enhancing classical geostatistical approaches. This integration opens up new opportunities for improving the accuracy of facies and sedimentological reconstructions. Aim. To systematize global experience in the application of machine learning methods for sedimentological and facies reconstructions of oil and gas reservoirs, identifying both already implemented solutions and alternative technologies at an early stage of adoption. Methods. A critical review of peer-reviewed studies covering Bayesian networks, variational autoencoders, generative adversarial networks, hybrid models, and classical geostatistical algorithms was conducted. The maturity of these technologies was assessed based on data types, expert involvement, and validation metrics. Results and conclusions. Machine learning methods go beyond simple spatial interpolation by uncovering complex, multidimensional relationships and reconstructing depositional scenarios. In practice, the use of generative and probabilistic graph models is expanding, underscoring the importance of multi-type data and geological context. Despite increasing automation, expert input remains critical – especially in Bayesian approaches. The main challenge remains the lack of sufficiently labeled training datasets; however, Bayesian methods demonstrate robustness even with limited data. A growing trend towards hybrid approaches that combine the strengths of machine learning and geostatistics has been observed, highlighting the continued importance of domain experts in modeling.
Keywords:
geological modelling, machine learning, facies modelling, sedimentology, Bayesian networks, generative models, alternative reservoir concepts
References:
1. Babordina O.A., Garanina M.P. Priority directions of the development strategy of fuel and energy complex enterprises of Russia in the conditions of the digital economy. Vestnik Samarskogo municipalnogo instituta upravleniya, 2021, no. 3, pp. 24–33. (In Russ.)
2. Abukova L.A., Dmitrievsky A.N., Eremin N.A. Digital modernization of Russia's oil and gas complex. Oil Industry, 2017, vol. 10, pp. 54–58. DOI: 10.24887/0028-2448-2017-10-54-58. (In Russ.)
3. Sarvaretidinov R.G., Sagitov D.K. Using a geological-mathematical model of a reservoir when comparing average values of porosity and permeability of reservoirs with different heterogeneity. Avtomatizatsiya, telemekhanizatsiya i svyaz v neftyanoy promyshlennosti, 2008, no. 10, pp. 15–20. (In Russ.)
4. Turova M.A., Stepanov A.V. Creation of 3D geological models of horizons V10, V12, V13 of one of the fields of the Nepa arch of Eastern Siberia. GeoEurasia 2018. Modern methods of studying and developing the subsurface of Eurasia. Proc. of the International Geological and Geophysical Conference. Moscow, February 5–8, 2018. Tver, PoliPRESS Publ., 2018. pp. 329–331. (In Russ.)
5. Higgs K.E., Crouch E.M., Raine J.I. An interdisciplinary approach to reservoir characterisation; an example from the early to middle Eocene Kaimiro Formation, Taranaki Basin, New Zealand. Marine and Petroleum Geology, 2017, vol. 86, pp. 111–139. DOI: 10.1016/j.marpetgeo.2017.05.018.
6. Yong H., Yongning M., Bincheng G., Zhaopu G., Wenxiang H. Application of stratigraphic-sedimentological forward modeling of sedimentary processes to predict high-quality reservoirs within tight sandstone. Marine and Petroleum Geology, 2019, vol. 101, pp. 540–555. DOI: 10.1016/j.marpetgeo.2018.11.027.
7. Chirkunov K., Gorelova A., Filippova Z., Popova O., Shokhin A., Zaitsev S. Modern look at uncertainty in conceptual geological modelling: development of the decision support system for petroleum exploration. Proc. SPE Annual Technical Conference and Exhibition. Dubai, 21–23 September 2021. pp.20–29. DOI: 10.2118/206078-MS.
8. Qi H.Sh., Chen M., Shen L.N., Cai F., Zhang A.M., Fang Q. Sedimentological and microfossil records of modern typhoons in a coastal sandy lagoon off southern China coast. Journal of Palaeogeography, 2021, vol. 10, no. 4, pp. 529–549. DOI: 10.1016/j.jop.2021.08.002.
9. Kundu S.N. Geoscience for petroleum engineers. 1st ed. Singapore, Springer Nature, 2023. 192 p. DOI: 10.1007/978-981-19-7640-7.
10. Gluyas J.G., Swarbrick R., Edward P. Petroleum Geoscience. 2nd ed. Hoboken, New Jersey, USA, Wiley-Blackwell, John Wiley & Sons, 2021. 432 p.
11. Morales-Hernández M., Sharif M.B., Gangrade S., Dullo T.T., Kao S.C., Kalyanapu A., Ghafoor S.K., Evans K.J., Madadi-Kandjani E., Hodges B.R. High-performance computing in water resources hydrodynamics. Journal of Hydroinformatics, 2020, vol. 22, no. 5, pp. 1217–1235. DOI: 10.2166/hydro.2020.163.
12. Schwarzacher W. Sedimentation in subsiding basins. Nature, 1966, vol. 210, pp. 1349–1350. DOI: 10.1038/2101349a0.
13. Barrell J. Rhythms and the measurements of geologic time. Geological Society of America Bulletin, 1917, vol. 28, pp. 745–904. DOI: 10.1130/gsab-28-745.
14. Bonham-Carter G.F., Sutherland A.J. Diffusion and settling of suspended sediment at river mouths: a computer simulation model. AAPG Bulletin, 1967, vol. 51, p. 2162. DOI: 10.1306/5d25c209-16c1-11d7-8645000102c1865d.
15. Pferd J.W. Computer simulation of geologic strata: a teaching tool. Computers & Geosciences, 1976, vol. 2, pp. 23–31. DOI: 10.1016/0098-3004(76)90089-3.
16. Tetzlaff D.M. Simulating clastic sedimentation. New York, Springer, 1989. 246 p.
17. Martinez P.A., Harbaugh J.W. Simulating Nearshore Environments. New York, Pergamon Press, 1993. 265 p.
18. Syvitski J.P.M. Computerized modeling of sedimentary systems. Book review. Marine Geology, 2000, vol. 170, no. 1–2, pp. 251–252. Available at: https://sci-hub.ru/10.1016/S0025-3227(00)00103-1 (accessed 15 September 2025).
19. Schlumberger. Available at: https://www.slb.com/about/who-we-are/our-history/2000s (accessed 18 September 2025).
20. Enlyft. Available at: https://enlyft.com/tech/products/petrel-e-p (accessed 18 September 2025).
21. Guo Q., Ren H., Yu J., Wang J., Liu J., Chen N. A method of predicting oil and gas resource spatial distribution based on Bayesian network and its application. Journal of Petroleum Science and Engineering, 2022, vol. 208, pp. 109267. DOI: 10.1016/j.petrol.2021.109267.
22. Lee K., Lim J., Choe J., Lee H.S. Regeneration of channelized reservoirs using history-matched facies-probability map without inverse scheme. Journal of Petroleum Science and Engineering, 2017, vol. 149, pp. 340–350. DOI: 10.1016/j.petrol.2016.10.046.
23. Nabawy B.S. New approaches in reservoir characterization utilizing conventional and special core analyses: a comprehensive review. Journal of Umm Al-Qura University for Applied Sciences, 2025, June, pp. 1–32. DOI: 10.1007/s43994-025-00225-6.
24. Yao J., Liu Q., Liu W., Chen X., Pan M. 3D reservoir geological modeling algorithm based on a deep feedforward neural network: a case study of the Delta reservoir of Upper Urho Formation in the X Area of Karamay, Xinjiang, China. Energies, 2020, vol. 13, no. 24, pp. 6699. DOI: 10.3390/en13246699.
25. Demyanov V.V., Saveleva E.A.; Geostatistics: theory and practice. Ed. by R.V. Arutyunyan. Moscow, Nauka Publ., 2010. 327 p. (In Russ.)
26. Krapu Ch., Hayes N., Stewart R., Kurte K., Rose A., Sorokine A., Urban M. A Bayesian model for multivariate discrete data using spatial and expert information with application to inferring building attributes. Spatial Statistics, 2023, vol. 55, p. 100745. DOI: 10.1016/j.spasta.2023.100745.
27. Chen M., Wu Sh., Bedle H., Xie P., Zhang J., Wang Y. Modeling of subsurface sedimentary facies using self-attention generative adversarial networks (SAGANs). Journal of Petroleum Science and Engineering, 2022, vol. 214, p. 110470. DOI: 10.1016/j.petrol.2022.110470.
28. Labourdette R., Hegre J., Imbert P., Insalaco E. Reservoir-scale 3D sedimentary modelling: approaches to integrate sedimentology into a reservoir characterization workflow. Geological Society, London, Special Publications, 2008, vol. 309, pp. 75–85. DOI: 10.1144/SP309.6.
29. Repina V.A. Probabilistic-statistical justification of the use of petrophysical properties of horizons in building hydrodynamic models of Tournaisian and Visean petroleum reservoirs of the Bashkir arch. Cand. Diss. Abstract. Perm, 2020. 115 p. (In Russ.)
30. Guartán J.A., Emery X. Predictive lithological mapping based on geostatistical joint modeling of lithology and geochemical element concentrations. Journal of Geochemical Exploration, 2021, vol. 227, p. 106810. DOI: 10.1016/j.gexplo.2021.106810.
31. Xu G., Zhang L., Pang X., Chen M., Xu S., Liu B., Zuo Y., Luo S., Hu L., Chen H., Li X., Wang X. New method for the reconstruction of sedimentary systems including lithofacies, environments, and flow paths: a case study of the Xisha Trough Basin, South China Sea. Marine and Petroleum Geology, 2021, vol. 133, p. 105268. DOI: 10.1016/j.marpetgeo.2021.105268.
32. Kingma D.P., Welling M. An introduction to variational autoencoders. Foundations and Trends in Machine Learning, 2019, vol. 12, pp. 307–392. DOI: 10.1561/2200000056.
33. Lee D., Ovanger O., Eidsvik J., Aune E., Skauvold J., Hauge R. Latent diffusion model for conditional reservoir facies generation. Computers & Geosciences, 2025, vol. 194, p. 105750. DOI: 10.1016/j.cageo.2024.105750.
34. Jo S., Ahn S., Park Ch., Kim Ja. Generative geomodeling based on flow responses in latent space. Journal of Petroleum Science and Engineering, 2022, vol. 211, p. 110177. DOI: 10.1016/j.petrol.2022.110177.
35. Arvanitidis G., Hauberg S., Schölkopf B. Geometrically enriched latent spaces. arXiv preprint arXiv:2008.00565, 2020, pp. 1–23. DOI: 10.48550/arXiv.2008.00565.
36. Sun Ch., Demyanov V., Arnold D. Geological realism in fluvial facies modelling with GAN under variable depositional conditions. Computational Geosciences, 2023, vol. 27, no. 2, pp. 203–221. DOI: 10.1007/s10596-023-10190-w.
37. Sun Ch., Demyanov V., Arnold D. A conditional GAN-based approach to build 3D facies models sequentially upwards. Computers & Geosciences, 2023, vol. 181, p. 105460. DOI: 10.1016/j.cageo.2023.105460.
38. Park T., Liu M.Y., Wang T.C., Zhu J.Y. Semantic image synthesis with spatially-adaptive normalization. Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, CA, USA, 2019. pp. 2337–2346.
39. Shishaev G., Demyanov V., Arnold D., Vygon R. History matching and uncertainty quantification of reservoir performance with generative deep learning and graph convolutions. Proc. ECMOR XXVIII. 18th European Conference on the Mathematics of Oil Recovery. Oslo, Norway, 6–9 September 2022. Houten, European Association of Geoscientists & Engineers, 2022. pp. 1–9. DOI: 10.3997/2214-4609.202244105.
40. Yu K., Cui Z., Sui X., Qiu X., Zhang J. Biological network inference with GRASP: a Bayesian network structure learning method using adaptive sequential Monte Carlo. Frontiers in Genetics, 2021, vol. 12, p. 764020. DOI: 10.3389/fgene.2021.764020.
41. Martinelli G., Eidsvik J., Hauge R., Førland M.D. Bayesian networks for prospect analysis in the North Sea. AAPG Bulletin, 2011, vol. 95, pp. 1423–1442. DOI: 10.1306/01031110110.
42. Masetti D., Fantoni R., Romano R., Sartorio D., Trevisani E. Tectonostratigraphic evolution of the Jurassic extensional basins of the Eastern Southern Alps and Adriatic Foreland based on an integrated study of surface and subsurface data. AAPG Bulletin, 2012, vol. 96, pp. 2065–2089. DOI: 10.1306/03091211087.
43. Svalova A., Walshaw D., Lee C., Demyanov V., Parker N.G., Povey M.J., Abbott G.D. Estimating the asphaltene critical nanoaggregation concentration region using ultrasonic measurements and Bayesian inference. Scientific Reports, 2021, vol. 11, no. 1, pp. 1–11. DOI: 10.1038/s41598-021-85926-8.
44. Azevedo L., Demyanov V. Multiscale uncertainty assessment in geostatistical seismic inversion. Geophysics, 2019, vol. 84, pp. 355–369. DOI: 10.1190/geo2018-0329.1.
45. Arnold D., Demyanov V., Rojas T., Christie M. Uncertainty quantification in reservoir prediction: Part 1 – model realism in history matching using geological prior definitions. Mathematical Geosciences, 2019, vol. 51, no. 2, pp. 209–240. DOI: 10.1007/s11004-018-9774-6.
46. Zahmatkesh I., Kadkhodaie A., Soleimani B., Azarpour M. Integration of well log-derived facies and 3D seismic attributes for seismic facies mapping: a case study from Mansuri oil field, SW Iran. Journal of Petroleum Science and Engineering, 2021, vol. 202, p. 108563. DOI: 10.1016/j.petrol.2021.108563.
47. Tiju V.I., Prakash T.N., Nair L.S., Sreenivasulu G., Nagendra R. Reconstruction of the paleoenvironment of the late Quaternary sediments of the Kerala coast, SW India. Journal of Asian Earth Sciences, 2021, vol. 222, p. 104952. DOI: 10.1016/j.jseaes.2021.104952.
48. Pondrelli M., Rossi A.P., Platz T., Ivanov A., Marinangeli L., Baliva A. Geological, geomorphological, facies and allostratigraphic maps of the Eberswalde fan delta. Planetary and Space Science, 2011, vol. 59, no. 11–12, pp. 1166–1178. DOI: 10.1016/j.pss.2010.10.009.
49. Gonzalez-Redin J., Luque S., Poggio L., Smith R., Gimona A. Spatial Bayesian belief networks as a planning decision tool for mapping ecosystem services trade-offs on forested landscapes. Environmental Research, 2016, vol. 144, pp. 15–26. DOI: 10.1016/j.envres.2015.11.009.
