The current state of oil reserves development is associated with problems of low oil recovery factor and high water cut. When searching for solutions to increase oil recovery, it is necessary to consider a whole range of factors affecting the displacement characteristics. Taking into account these factors involves working with large sets of reservoir data. The success of decisions made in selecting the management scenario for the development of the studied field is directly dependent not only on the quality of the available reservoir data but also on the computational tools used to guide these decisions during specific hydrodynamic stimulation operations. Therefore, critical importance is placed on enhancing the performance of software products used for reservoir forecasting and improving input data quality by identifying and removing «bad» data. Concurrent fulfilment of these conditions significantly boosts the effectiveness of decision-making during the forecasting phase. This paper outlines the technology for optimizing management decisions for field development based on the TEICS ONE suite. The core architecture of the computational suite is described, along with the sequential stages of the technology. The application results at the field, operated by Belkamneft JSC demonstrate the potential to maximize the recovery of reserves in late-stage fields and achieve the target oil recovery factor by effectively utilizing historical development data and making rational decisions for field management.
References
1. Gladkov E.A., Geologicheskoe i gidrodinamicheskoe modelirovanie mestorozhdeniy nefti i gaza (Geological and hydrodynamic modeling of oil and gas fields), Tomsk: Publ. of TPU, 2012, 99 p.
2. Volodin E.M., Zakharova A.A., The use of supercomputers for acceleration filtration process based on 3D geological and hydrodynamic models of oil and gas fields
(In Russ.), Doklady TUSUR, 2010, no. 2-2(22), pp. 241–244.
3. Dieva N.N., Aminev D.A., Kravchenko M.N. et al., Overview of the application of physically informed neural networks to the problems of nonlinear fluid flow in porous media, Computation, 2024, V. 12(4), no. 69, DOI: http://doi.org/10.3390/computation12040069
4. Vol’pin S.G. et al., Verifikatsiya gidrodinamicheskikh modeley po dannym promyslovykh issledovaniy skvazhin dlya poiska tselikov nefti (Verification of hydrodynamic models based on field well survey data for oil exploration), Moscow: Publ. of Scientific Research Institute of System Analysis, 2020, 132 p.
5. Muslimov R.Kh., History and prospects of hydrodynamic methods for oil fields development in Russia (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2020, no. 12, pp. 96–100, DOI: http://doi.org/10.24887/0028-2448-2020-12-96-100
6. Hui Zhao, Lingfei Xu, Zhenyu Guo et al., Flow-path tracking strategy in a data-driven interwell numerical simulation model for waterflooding history matching and performance prediction with infill wells, SPE-199361-PA, 2019, DOI: http://doi.org/10.2118/199361-PA
7. Yousef A.A., Gentil P.H., Jensen J.L., Lake L.W., A capacitance model to infer interwell connectivity from production and injection rate fluctuations, SPE-95322-MS, 2006, DOI: http://doi.org/10.2118/95322-PA
8. Zhao H., Kang Z., Zhang X. et al., INSIM: A data-driven model for history matching and prediction for waterflooding monitoring and management with a field application, SPE-173213-MS, 2015, DOI: http://doi.org/10.2118/173213-MS
9. Albertoni A., Lake L.W., Inferring connectivity only from well-rate fluctuations in water floods, SPE-83381-PA, 2003, DOI: http://doi.org/10.2118/83381-PA
10. Guo Z., Reynolds A.C. A physics-based data-driven model for history-matching, prediction and characterization of waterflooding performance, SPE-182660-MS, 2017, DOI: https://doi.org/10.2118/182660-PA
11. Zhao H., Liu W., Rao X. et al., INSIM-FPT-3D: a data-driven model for history matching,water-breakthrough prediction and well-connectivity characterization in three-dimensional reservoirs, SPE-203931-MS, 2021, DOI: http://doi.org/10.2118/203931-MS
12. Ovsepian M., Lys E., Cheremisin A. et al., Testing the INSIM-FT proxy simulation method, Energies, 2023, V. 16, no. 4, DOI: http://doi.org/10.3390/en16041648
13. Klimova E.G., A stochastic ensemble Kalman filter with perturbation ensemble transformation (In Russ.), Sibirskiy zhurnal vychislitel’noy matematiki = Numerical Analysis and Applications, 2019, V. 22, no. 1, pp. 27–40, DOI: https://doi.org/10.15372/SJNM20190103
14. Bakhitov R.R., Application of machine learning algorithms in tasks of well productivity index forecasting for carbonate oil fields (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2019, no. 9, pp. 82–85, DOI: http://doi.org/10.24887/0028-2448-2019-9-82-85
15. Amerkhanov R.M., Gilyazov A.Kh., D’yakonov A.A. et al., Optimization of production well operation through combination of engineering approach, computer programming and machine learning methods (In Russ.), Neftyanoe khozyaystvo = Oil Industry, 2024, no. 8, pp. 94–99, DOI: http://doi.org/10.24887/0028-2448-2024-8-94-99
