Integration of machine learning methods and geological and hydrodynamic modeling in field development design

UDK: 622.276.1./.4712.8
DOI: 10.24887/0028-2448-2022-3-48-53
Key words: reservoir engineering, enhanced oil recovery (EOR) methods, neural networks, hydrodynamic modeling
Authors: L.S. Brilliant (TOGI LLC, RF, Tyumen), A.S. Zavialov (TOGI LLC, RF, Tyumen), M.U. Danko (TOGI LLC, RF, Tyumen), K.A. Andronov (TOGI LLC, RF, Tyumen), I.V. Shpurov (State Commission on Mineral Resources, RF, Moscow; Saint-Petersburg Mining University, RF, Saint-Petersburg; Lomonosov Moscow State University, RF, Moscow), V.G. Bratkova (State Commission on Mineral Resources, RF, Moscow), A.V. Davydov (State Commission on Mineral Resources, RF, Moscow)

Maintaining oil production at long-term developed fields requires solving the problem of high production costs. This problem is associated with the need to withdraw significant volumes of produced water and a proportionally high need for injection in order to maintain reservoir pressure. It is noted that a 1% reduction in water cut in production makes it possible to reduce operating costs in oil production by up to 15%. It is shown that the problems of effective development of mature fields are associated with the solution of the optimization problem of distributing fluid production and water injection in the wells system. The authors argue the idea that at the later stages of development, the priority for hydrodynamic modeling should be tools based on solving the inverse problem of hydrodynamics, providing for the widespread use of material balance methods and allowing big data processing. A new concept of combining artificial intelligence methods and a hydrodynamic model is proposed. The concept provides for obtaining a functional relationship between the historical oil production rate and injectivity using a neural network, searching for the maximum oil production and its distribution. At the same time, only one calculation is performed on the hydrodynamic model, which significantly reduces time costs. An example of the application of the proposed technology is given. It is concluded that the set of methodological, mathematical and informational solutions presented in the article will allow formalizing the processes of designing hydrodynamic methods for enhanced oil recovery, clarifying the model for a feasibility study of profitable and technologically recoverable oil reserves.


1. Vygon Consulting. Nalogi v neftedobyche: reforma 2020 (Vygon Consulting. Taxes in oil production: reform 2020), URL: 0b6/vygon_consulting_tax_reform_2020.pdf.

2. Kozlova D.V., “Umnaya” dobycha: pochemu tsifrovye tekhnologii uderzhat nizkie tseny na neft' (Smart mining: why digital technologies will keep oil prices low), URL:

3. Garifulin A.R., Slivka P.I., Gabdulov R.R., “Smart wells“ - System of automated control over oil and gas production (In Russ.), Neftʹ. Gaz. Novatsii, 2017, no. 12, pp. 24–32.

4. Ryabets D.A., Beskurskiy V.V., Brilliant L.S. et al., Production management based on neural network optimization of well operation modes at the BS8 facility of the Zapadno-Malobalykskoye field (In Russ.),, 2019, no. 9, URL:

5. Patent RU 2 759 143 C1, Method for increasing the efficiency of hydrodynamic methods for increasing the petroleum recovery of a reservoir, Inventors: Brilliant L.C., Zav'yalov A.S., Dan'ko M.Yu., Elisheva A.O., Andonov K.A., Tsinkevich O.V.

6. Patent RU 2 614 338 C1, Method of real-time control of reservoir flooding, Inventors: Brilliant L.S., Komyagin A.I., Blyashuk M.M., Tsinkevich O.V., Zhuravleva A.A.

7. Patent RU 2 565 313 C2, Operations control method for reservoir flooding, Inventors: Brilliant L.S., Smirnov I.A., Komjagin A.I., Potrjasov A.V., Pechorkin M.F., Baryshnikov A.V.

8. Patent RU 2 715 593 C1, Method of operative control of water flooding of formations, Inventors: Brilliant L.S., Zav'yalov A.S., Dan'ko M.Yu.

9. Brilliant L.S., Dulkarnaev M.R., Dan'ko M.Yu. et al., Challenges of efficient brownfield development: architecture of digital solutions in control of well operation conditions (In Russ.), Nedropol'zovanie XXI vek, 2020, no. 4, pp. 98-107.

10. Potryasov A.A., Mazitov M.R., Nikiforov S.S. et al., Management over oil field flooding process at the basis of proxy modeling (In Russ.), Neft'. Gaz. Novatsii, 2014, no. 12, pp. 32-37.

11. Aref'ev S.V., Yunusov R.R., Valeev A.S. et al., Methodical foundations and experience in the implementation of digital technologies for operational planning and management of the operating modes of production and injection wells in the OPR area of the YuV1 reservoir of the Vatjeganskoye deposit of the Povkhneftegaz TPP (OOO LUKOIL-Western Siberia) (In Russ.), Nedropol'zovanie XXI vek, 2017, no. 6, pp. 60-81.

12. Brilliant L.S., Gorbunova D.V., Zav'yalov A.S. et al., Automation of processes for managing the operation modes of injection wells with neural network optimization at the BS8 facility of the Zapadno-Malobalykskoye field (In Russ.),, 2020, no. 2, pp. 52-57.

13. Zarubin A.L., Perov D.V., Ryabets D.A. et al., Automation of neural network optimization processes for water injection at the fields of "OC "Neftisa" JSC (In Russ.), Neft'. Gaz. Novatsii, 2020, no. 8, pp. 40-53.

To buy the complete text of article (a format - PDF) or to read the material which is in open access only the authorized visitors of the website can. .

Mobile applications

Read our magazine on mobile devices

Загрузить в Google play