Modeling the permeability of carbonate reservoirs using a two-parameter distribution and ML inversion

UDK: 622.276.031.011.43:51

DOI: 10.24887/0028-2448-2025-12-26-29

Key words: three-dimensional geological model, permeability coefficient, laboratory core studies, machine learning methods, complex reservoir, cavernosity, fracturing

Authors: Sh.Kh. Sultanov1,2 (Ufa State Petroleum Technological University, RF, Ufa; Academy of Sciences of the Republic of Bashkortostan, RF, Ufa); A.A. Makhmutov1,2 (Ufa State Petroleum Technological University, RF, Ufa; Academy of Sciences of the Republic of Bashkortostan, RF, Ufa); R.U. Rabaev (Ufa State Petroleum Technological University, RF, Ufa); D.V. Silnov (Ufa State Petroleum Technological University, RF, Ufa; RN-BashNIPIneft LLC, RF, Ufa); O.R. Privalova (RN-BashNIPIneft LLC, RF, Ufa; Ufa University of Science and Technology, RF, Ufa); R.G. Nigmatullina (RN-BashNIPIneft LLC, RF, Ufa); Yu.B. Lind (RN-BashNIPIneft LLC, RF, Ufa); V.M. Chilikin (Ufa State Petroleum Technological University, RF, Ufa); A.R. Sharafutdinov (Ufa State Petroleum Technological University, RF, Ufa); E.M. Makhnitkin (Ufa State Petroleum Technological University, RF, Ufa); Yu.A. Abusal (Ufa State Petroleum Technological University, RF, Ufa)

Nowadays, due to the depletion of reserves in areas with increased filtration and capacitance properties, the study of geological structure of complex objects is becoming particularly relevant, dictating the need to find ways to reliable geological and hydrodynamic modeling. The object under study is characterized by a complex geology, thus standard approaches to constructing geological and hydrodynamic models demonstrate low accuracy in the inner-well space. The adaptation of the filtration model is very difficult and requires the addition of fictitious aquifers, modifiers, etc., without which it shall not reflect the actual picture of oil filtration. This article presents an algorithm for constructing a permeability cube that enables taking into account the following complicating factors: the void space of the reservoir (due to Flow Zone Indicators), the influence of fault tectonics, and a small amount of information from wells (including horizontal). The algorithm includes the use of machine learning methods «random forest» and ML inversion of seismic, as well as a two-parameter distribution tool that enables to take into account the distribution of point information (primary attribute) due to the correlation with the seismic cube (secondary attribute). The paper identifies 4-5 reservoir classes (petroclasses) for each reservoir and constructs new correlations of the permeability-porosity type. The verification of the constructed 3D cubes of the permeability coefficient with the data obtained from the petrophysical description of the core from exploration and production wells showed high convergence in the borehole of the cube obtained using a two-parameter distribution.

References

1. Semanov A.S., Semanova A.I., Fattakhov I.G. et al., Modeling tools used for operational field development management (In Russ.), Neftegazovoe delo, 2023, no. 5,

pp. 91–98, DOI: https://doi.org/10.17122/ngdelo-2023-5-91-98

2. Makhmutov A.A., Shabrin N.V., Malyarenko A.M. et al., Improving methods of three-dimensional geological models of oil fields with complex structure (In Russ.), Geologiya. Izvestiya Otdeleniya nauk o Zemle i prirodnykh resursov, 2023, no. 30, pp. 62–80, DOI: https://doi.org/10.24412/2949-4052-2023-1-62-80

3. Bakirov I.I., Makhmutov A.A., Minnullin A.G. et al., Experience of oil-saturated cube simulation in reservoirs, heterogeneous in their reservoir characteristics, at the latest stage of their development (In Russ.), Geologiya, geofizika i razrabotka neftyanykh i gazovykh mestorozhdeniy, 2017, no. 12, pp. 69–70.

4. Sten’kin A.V., Kotenev Yu.A., Sultanov Sh.Kh., Umetbaev V.G., Methodical substantiation of increasing production of oil reserves on the fields complicated by tectonic disturbances (In Russ.), Izvestiya Tomskogo politekhnicheskogo universiteta. Inzhiniring georesursov = Bulletin of the Tomsk Polytechnic University, 2019, no. 1,

pp. 214–223, DOI: https://doi.org/10.18799/24131830/2019/1/71

5. Bakhtizin R.N., Lutfullin A.A., Makhmutov A.A., Improvement of the methodology for modeling the permeability cube taking into account the heterogeneity of the structure of the pore space of the pay zones of the South Tatar arch (In Russ.), Neftegazovoe delo, 2023, V. 21, no. 2, pp. 25–34, DOI: https://doi.org/10.17122/ngdelo-2023-2-25-34

6. Chudinova D.Yu., Kotenev A.Yu., Makhnytkin E.M. et al., The influence of geological structure productive sediments Middle Ob on efficiency production enhancement operations (In Russ.), Geologiya. Izvestiya Otdeleniya nauk o Zemle i prirodnykh resursov, 2023, no. 32, pp. 38–51, DOI: https://doi.org/10.24412/2949-4052-2023-3-38-51

7. Mel’nikov A.V., Sultanov Sh.Kh., Makhmutov A.A., Chibisov A.V., Drilling challenges and technological solutions in the development of oil deposits in fractured carbonate reservoirs (In Russ.), Nanotekhnologii v stroitel’stve, 2024, V. 16, no. 6, pp. 567–575, DOI: https://doi.org/10.15828/2075-8545-2024-16-6-567-575

8. Mustafaev M.K., Sultanov Sh.Kh., Makhmutov A.A. et al., Improving the reliability of the three-dimensional geological basis of complex development targets (In Russ.), Neftegazovoe delo, 2024, V. 22, no. 5, pp. 8–16, DOI: https://doi.org/10.17122/ngdelo-2024-5-8-16

9. Mustafaev M.K., Izuchenie vliyaniya neodnorodnosti produktivnykh plastov po FES na kharakter raspredeleniya neftenasyshchennosti (Study of the influence of heterogeneity of productive formations by reservoir properties on the nature of oil saturation distribution), Proceedings of International scientific and practical conference dedicated to the 75th anniversary of the Mining and Petroleum Faculty of Ufa State Petroleum Technical University and the 100th anniversary of the scientist Alexander Ivanovich Spivak, Ufa, 2023, p. 190.

10. Yatsenko V.M., Antonenko D.A., Nigmatullin R.R., The technique of permeability estimation by a method of hydraulic units on an example of Vankorskoye field reservoirs (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2009, no. 12, pp. 69–72.

11. Amaefule J.O., Altunbay M., Tiab D. et al., Enhanced reservoir description: Using core and log data to identify hydraulic (flow) units and predict permeability in uncored intervals/wells, SPE-26436-MS, 1993, DOI: https://doi.org/10.2118/26436-MS

12. Zalevskiy O.A., Kotenev Yu.A., Sultanov Sh.Kh., Sharafutdinov A.R., Identification of lithological and facies features of sediments based on machine learning methods (In Russ.), Neftegazovoe delo, 2024, V. 22, no. 6, pp. 16–25, DOI: https://doi.org/10.17122/ngdelo-2024-6-16-25

13. Sharafutdinov A.R., Sultanov Sh.Kh., Chilikin V.M., The application of machine learning algorithms to detail the geological structure of productive sedimentary rocks

(In Russ.), Inzhener-neftyanik, 2025, no. 1, pp. 86–89.