G.G. Faizrakhmanov, I.I. Khairullin, R.R. Khasanov, V.A. Sosnitskaya, R.V. Ryzhov
DOI: https://doi.org/10.25689/NP.2023.3.73-83
Abstract
This paper presents the experience of using machine learning methods to predict the technological indicators of the development of wells operating in carbonate reservoirs. The stages of creating, training a recurrent neural network with a long short-term memory in a test area (small deposit) and subsequent forecasting of oil flow rate by wells for a 3-6 month perspective are described. In order to evaluate the effectiveness of this approach, a test was carried out on a control sample and the forecast results were compared with forecasting by alternative methods, and in particular with forecasts of the geological and hydrodynamic model, the dip curve and the material balance model. Modeling object carbonate deposits of oil field N, located in the Volga-Ural oil and gas province.
References
2. Hamid Rahmanifard; Ian Gates; Abdolmohsen Shabib Asl Comparison of Machine Learning and Statistical Predictive Models for Production Time Series Forecasting in Tight Oil Reservoirs // Paper presented at the SPE/AAPG/SEG Unconventional Resources Technology Conference, Houston, Texas, USA, June 2022. https://doi.org/10.15530/urtec-2022-3703284 (in English)
3. Nazarenko M.Yu., Zolotukhin A.B. Application of machine learning for probabilistic production forecasting and ultimately recoverable reserves estimation. Neftyanoe Khozyaistvo [Oil Industry]. 2020, No. 9, pp. 109-113 (in Russian)
4. Zotkin O.V., Simonov M.V., Osokina A.E., Andrianova A.M., Margarit A.S., Timoshenko V.A., Lebedev S.F. The new approach to improvement oil reservoir proxy model predictions using machine learning algorithms. Neftyanoe Khozyaistvo [Oil Industry]. 2019, No. 12, pp. 60-63 (in Russian)
5. Hochreiter, Sepp & Schmidhuber, Jurgen. Long Short-term Memory. Neural computation. 1997. V. 9, No. 8, pp. 1735-1780. DOI: 10.1162/neco.1997.9.8.1735. (in English)
Authors
G.G. Faizrakhmanov, PhD Candidate, Unconventional Reserves Development Department, Institute of Geology and Petroleum Technologies, Kazan Federal University
4/5, Kremlevskaya st., Kazan, 420008, Russian Federation
E-mail: galimfaizrakhmanov1995@gmail.com
I.I. Khairullin, PhD Candidate, Oil and Gas Field Development Department, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: ilnur616@yandex.ru
R.R. Khasanov, PhD Candidate, Oil and Gas Field Development Department, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: khasanovramzil@gmail.com
V.A. Sosnitskaya, PhD Candidate, Oil and Gas Field Development Department, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: valeriyasosnitskaya@yandex.ru
R.V. Ryzhov, PhD Candidate, Oil and Gas Field Development Department, Almetyevsk State Petroleum Institute
2, Lenin st., Almetyevsk, 423450, Russian Federation
E-mail: rom.ryzhoff2011@yandex.ru
For citation:
G.G. Faizrakhmanov, I.I. Khairullin, R.R. Khasanov, V.A. Sosnitskaya, R.V. Ryzhov Prognozirovaniye dinamiki izmeneniya debita nefti s pomoshch'yu metodov mashinnogo obucheniya [Forecasting the dynamics of oil flow rate changes using machinne learning methods]. Neftyanaya Provintsiya, No. 3(35), 2023. pp. 73-83. DOI https://doi.org/10.25689/NP.2023.3.73-83. EDN PIFPLA (in Russian)