A.V. Pinchuk, E.A. Pylev, E.E. Polyakov, I.V. Churikova, M.A. Tvorogov, D.N. Krylov, V.M. Pishchukhin
Real-time drilling support, hydrocarbon reserves monitoring and geological modeling based on artificial intelligence technology
DOI 10.47148/0016-7894-2025-4-77-87
Key words: field; neural network; horizontal well; seismic exploration; drilling; geoseismic model; lithology volume; reservoir; net thickness prediction; reserves assessment.
For citation: Pinchuk A.V., Pylev E.A., Polyakov E.E., Churikova I.V., Tvorogov M.A., Krylov D.N., Pishchukhin V.M. Real-time drilling support, hydrocarbon reserves monitoring and geological modeling based on artificial intelligence technology. Geologiya nefti i gaza. 2025;(4):77–87. DOI: 10.47148/0016-7894-2025-4-77-87. In Russ.
This paper presents the methodology and stages of integrated seismic and well log data interpretation using neural network approaches in development drilling, which is aimed at predicting the optimal placement of each production well with horizontal sidetrack in a well pad on the basis of geological model that is being continuously history matched in the target horizons. Examples and reliability assessment of implementation of neural network prediction technology in development drilling are considered. Based on drilling results, the average accuracy of predicting net reservoir thicknesses reached 0.70. The paper outlines criteria for determining the optimal direction of well drilling. An alternative integrated neural network–based approach to building geological model of the studied reservoir is presented. Practical case studies confirm that interpolation methods in conventional geomodelling fail to reproduce reservoir heterogeneity in the interwell space, whereas neural network-based models allow doing this. The advantages of the neural network-based geological model over the interpolation approach are demonstrated, particularly in capturing details and consistent facies trends both laterally and in reservoir section. The level of heterogeneity is on the order of one grid cell – 50 m or more laterally, and 5 to 7 m vertically (in terms of effective thickness). The conclusions and recommendations obtained are confirmed by subsequent drilling of 70 development wells..
Anatolii V. Pinchuk
Chief Specialist
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: A_Pinchuk@vniigaz.gazprom.ru
Evgenii A. Pylev
Candidate of Geographic Sciences, Acting Deputy General
Director for Science, Head of the Development Center
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: E_Pylev@vniigaz.gazprom.ru
Evgenii E. Polyakov
Doctor of Geologo-Mineralogical Sciences,
Chief Researcher
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: E_Polyakov@vniigaz.gazprom.ru
Irina V. Churikova
Head of Laboratory
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: I_Churikova@vniigaz.gazprom.ru
Mikhail A. Tvorogov
Chief Specialist
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: M_Tvorogov@vniigaz.gazprom.ru
Dmitrii N. Krylov
Doctor of Technical Sciences,
Chief researcher
Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: D_Krylov@vniigaz.gazprom.ru
Vasilii M. Pishchukhin
Candidate of Technical Sciences, Academician of the Academy of
Sciences of Applied Radio Electronics, Corresponding Member of
Russian Academy of Natural Sciences in the Oil and Gas Section,
Leading Resercher at Gazprom VNIIGAZ,
15, str. 1 Proyektiruyemy proyezd № 5537, Razvilka, Vidnoe,
Moscow region, 142717, Russia
e-mail: V_Pischukhin@vniigaz.gazprom.ru
SPIN: 4175-1144
1. Ol’neva T.V., Egorov A.S., Oreshkova M.Yu. Improvement of seismic image in interpretation stage for the purposes of seismic facies analysis. Geologiya nefti i gaza. 2023;(6):81–95. DOI: 10.47148/0016-7894-2023-6-81-95. In Russ.
2. Ol’neva T.V., Zhukovskaya E.A. Sposob prognozirovaniya morfometricheskikh parametrov ruslovykh tel (paleokanalov) [Method for predicting morphometric parameters of channel bodies (paleochannels)]: Patent RF № 2672766. 2018.
3. Malyarova T., Kopenkin R. Tekhnologiya neironnoi inversii dlya prognoza svoistv rezervuarov po seismicheskim dannym [Neural inversion technology for predicting reservoir properties based on seismic data.]. Khimstal’kon. Available at: https://www.himstalcon.ru/articles/tehnologiya-neyronnoy-inversii-dlya-prognoza-svoystv-rezervuarov-po-seysmicheskim-dannyim?ysclid=mdpuddj35b517766724 (accessed 19.03.2025).
4. Pinchuk A.V., Pylev E.A., Polyakov E.E., Tvorogov M.A., Churikova I.V. Optimisation of cluster drilling based on integrated seismic attributes and well log data analysis using neural network algorithms: Chayandinsky oil and gas condensate field. Geologiya nefti i gaza. 2022;(2):17–30. DOI: 10.31087/0016-7894-2022-2-17-30. In Russ.