Регистрация
Уже зарегистрированы? Авторизоваться
Забыли пароль?
Введите e-mail, и мы поможем его восстановить
Вспомнил пароль! — Войти
Проверяйте почту, чтобы сменить пароль
Вспомнил пароль! — Войти
Вы авторизованы
Neftyanaya Provintsiya
ISSN 2412-8910 (Online)
electronic peer-reviewed scholarly publication
No. 4(44), 2025
Neftyanaya provintsiya No. 4(44), 2025

Improving the efficiency of gas field development by redistributing well production using machine learning

A.Yu. Yushkov, V.A. Ogai, R.N. Khakimov, N.D. Bulychev, Yu.G. Fedoreev
DOI: https://doi.org/10.25689/NP.2025.4.221-234

Download article

Abstract


The task of optimal control of gas field development, in particular the task of well rate regulation, is a relevant one. The article shows that rate regulation during the period of constant production affects the gas recovery factor (GRF). Machine learning was used to derive the relationship between the optimal target production rate and the known well parame­ters. To form a training dataset, "synthetic" hydrodynamic models of gas deposits were created, simulating 40 different development scenarios differing in the number and location of wells. For each development scenario, the best rate allocation options were obtained using optimiza­tion tools and included in the training dataset. The implemented model uses the Random Forest algorithm. In a test case, when allocating rates based on the ML model, the accumulated dis­counted incremental gas production amounted to 164 million m³ (+0.56% to GRF) compared to the reference distribution (optimizer), plus 255 million m³, which indicates the applicability of the tool as a fast (but less accurate) alternative to the optimizer. It is concluded that pre-trained ML models can be used within optimization algorithms to obtain a "first approximation" solution, which significantly speeds up the subsequent search for the optimum.

Key words:

Gas field development, production strategy, gas flow rate, optimization, machine learning, hydrodynamic modeling

References

1. Arkhipov Yu.A. Sovershenstvovanie metodov obosnovaniya rezhimov raboty gazovykh skvazhin [Improvement of methods for substantiating the operating modes of gas wells]. Moscow, 2011. 159 p. (in Russian)

2. Pospelova T.A., Arzhilovsky A.V., Kharitonov A.N., Yushkov A.Yu., Strekalov A.V., Lopatin R.R., Loznyuk O.A., Arkhipov Yu.A. Kontseptsiya intellektualizatsii gazovykh i gazokondensatnykh promyslov [The concept of intellectualization of gas and gas-condensate fields]. Neftyanoe Khozyaystvo [Oil Industry], 2019, no. 11, pp. 58-63. (in Russian)

3. Nazarov A.V. Razvitie metodov matematicheskogo modelirovaniya dlya proektirovaniya i analiza razrabotki neftegazokondensatnykh mestorozhdeniy [Development of mathematical modeling methods for the design and analysis of oil and gas condensate field development]. Ukhta, 2012. 427 p. (in Russian)

4. Trubacheva I.A., Ermolaev A.I., Nekrasov A.A. Metod raspredeleniya zadannogo otbora gaza po skvazhinam gazokondensatnogo mestorozhdeniya s tsel'yu uvelicheniya kondensatootdachi [A method for allocating a given gas production rate among wells of a gas-condensate field to increase condensate recovery]. Avtomatizatsiya, telemekhanizatsiya i svyaz' v neftyanoi promyshlennosti [Automation, Telemechanization and Communication in the Oil Industry], 2018, no. 3, pp. 35-40. (in Russian)

5. Ermolaev A.I., Nekrasov A.A., Trubacheva I.A. Raspredelenie zadannogo summarnogo otbora gaza po skvazhinam gazokondensatnoi zalezhi po kriteriyu minimuma poter' plastovoi energii [Allocation of a given total gas production rate among wells of a gas-condensate pool based on the criterion of minimum reservoir energy loss]. Nauka i tekhnika v gazovoi promyshlennosti [Science and Technology in the Gas Industry], 2019, no. 2(78), pp. 57-67. (in Russian)

6. Shayakhmetov A.I. Prognozirovanie obvodneniya fonda dobyvayushchikh skvazhin na krupnykh gazovykh mestorozhdeniyakh [Forecasting water breakthrough in the stock of production wells at large gas fields]. Ufa, 2014. 144 p. (in Russian)

Authors

A.Yu. Yushkov, PhD in Technical Sciences, Senior Expert in Gas Field Development, RN-Geology Research and Development LLC
79/1, Osipenko St., Tyumen, 625002, Russian Federation
E-mail: ayyushkov@rn-gir.rosneft.ru

V.A. Ogai, Head of Research Support Group, RN-Geology Research and Development LLC
79/1, Osipenko St., Tyumen, 625002, Russian Federation
E-mail: vaogay@tnnc.rosneft.ru

R.N. Khakimov, Master's student, Tyumen Industrial University
70, Melnikayte St., Tyumen, 625027, Russian Federation
E-mail: renat.khakimov03@mail.ru

N.D. Bulychev, Master's student, Tyumen Industrial University
70, Melnikayte St., Tyumen, 625027, Russian Federation
E-mail: nikitabul2004@gmail.com

Yu.G. Fedoreev, Master's student, Gubkin Russian State University of Oil and Gas (National Research University)
65k1, Leninsky Prospekt, Moscow, 119296, Russian Federation
E-mail: fedoreev.4@gmail.com

For citation:

A.Yu. Yushkov, V.A. Ogai, R.N. Khakimov, N.D. Bulychev, Yu.G. Fedoreev Povysheniye effektivnosti razrabotki gazovykh mestorozhdeniy za schet pereraspredeleniya otborov mezhdu skvazhinami s ispol'zovaniyem mashinnogo obucheniya [Improving the efficiency of gas field development by redistributing well production using machine learning]. Neftyanaya Provintsiya, No. 4(44), 2025. pp. 221-234. DOI https://doi.org/10.25689/NP.2025.4.221-234. EDN EYXTCV (in Russian)

NEFTYANAYA PROVINTSIYA
electronic peer-reviewed scholarly publication
Main
Editorial board
Editorial Policy
For authors
Review Procedure
About journal
Archive
Contacts
(85594) 4-14-65
vkro-raen@yandex.ru
Russia, Republic of Tatarstan, Bugulma, Voroshilova Str., 21
© Non-governmental organization Volga-Kama Regional Division of the Russian Academy of Natural Science, 2015-2025 All the materials of the journal are available under the Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/)
Made on Bazium Bazium