Release:
2025. Vol. 11. № 1 (41)About the authors:
Vitaly P. Kosyakov, Senior Researcher, Khristianovich Institute of Theoretical and Applied Mechanics of the Siberian Branch of the Russian Academy of Sciences, Tyumen, Russia; Senior Researcher, Laboratory of Scientific Engineering (Advanced Petroleum Engineering School), Almetyevsk State Technological University “Petroleum Higher School”, Almetyevsk, RussiaAbstract:
The paper proposes an approach to solve the problem of missing data in pressure measurements at an oilfield. Currently, the use of hydrodynamic models is a mandatory requirement for a field development system. Mathematical models are used in calculating technological development indicators during the preparation of a development project or during its support. The main input data that characterize reservoir energy are pressure measurements, which are less accurate than other field measurements such as production and injection. To recover missing pressure measurements, a common practice is to rely on the latest measurements, which may ignore dynamic changes in other variables and lead to inconsistent data. While this approach may be effective for some cases, it may not be reliable when there are multiple missing measurements. An alternative is to use simplified hydrodynamic models to address missing pressure issues. These models allow for quick optimization and multidimensional computations while staying within physical constraints. A demonstration is provided by using a synthetic flow model to replace missing pressure values, considering multivariant model parameters. Optimization is done using a multistart technique with initial guesses generated by the Latin hypercube sampling method. The quality of results is assessed using cross-validation and the predictive ability of the model is evaluated by splitting the modeling time into training and testing segments.References:
Aziz, Kh., & Settari, A. (2004). Petroleum reservoir simulation. Izhevsk Institute of Computer Science. [In Russian]
Andreev, V. B. (2013). Numerical methods. MAX Press. [In Russian]
Basniev K. S., Dmitriev N. M., Kanevskaya R. D., Maksimov V. M. (2006). Underground Hydromechanics. Moscow-Izhevsk: Institute of Computer Research. 488 p. [In Russian]
Bekman, A. D., Pospelova, T. A., & Zelenin, D. V. (2020). A new approach to water cut forecasting based on results of capacitance resistance modeling. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, 6(1), 192–207. https://doi.org/10.21684/24117978-2020-6-1-192-207 [In Russian]
Galkin V.I., Ponomareva I.N., Martyushev D.A. (2021). Forecast of reservoir pressure and study of its behavior during development of oil fields based on the construction of multi-level multidimensional probabilistic-statistical models // Georesursy, 23(3), 73-82. DOI: 10.18599/grs.2021.3.10
Mazo A.B., Potashev K. A. (2020). Superelementy. Modelirovanie razrabotki neftyanykh mestorozhdeniy. Moskva : INFRA-M. 219p. [In Russian]
Potashev K.A., Akhunov R.R., Mazo A.B. (2022). Calculation of the flow rate between wells in the flow model of an oil reservoir using streamlines // Georesources. 24(1), pp. 27–35. https://doi.org/10.18599/grs.2022.1.3 [In Russian]
Umanovskiy A. W. (2022). Proxy modeling pf reservoir hydrodynamics with graph neural networks // Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy. Vol. 8. No 3 (31). P. 155-177. https://doi.org/10.21684/2411-7978-2022-8-3-155-177 [In Russian]
Kharisov M. N., Yunusova E. A., Kharisova E. A., Mayskiy R. A. 2018. Algorithm for determining displacement characteristics under conditions of data imperfection // Neftegazovoe delo, 16(6), 20-25. DOI: 10.17122/ngdelo-2018-6-20-25
Shokina, M. O. (2017). Application of k-means++ algorithm for clustering sequences with unknown number of clusters / M. O. Shokina // Novye informatsionnye tekhnologii v avtomatizirovannykh sistemakh, 20, 160-163.
SciPy, optimization // Habr. 2019. February 7. Retrieved January 27, 2025, from https://habr.com/ru/articles/439288/
Guo, Z., & Reynolds, A.C. 2019. INSIM-FT-3D: A Three-Dimensional Data-Driven Model for History Matching and Waterflooding Optimization. Paper presented at the SPE Reservoir Simulation Conference (April 11, 2019, Galveston, Texas, USA). https://doi.org/10.2118/193841-MS
Holanda, R. W. d., Gildin, E., Jensen, J. L., Lake, L. W., & Kabir, C. S. (2018). A State-of-the-Art Literature Review on Capacitance Resistance Models for Reservoir Characterization and Performance Forecasting. Energies. 11(12) Art. 3368. https://doi.org/10.3390/en11123368
Illarionov E., Temirchev P., Voloskov D., Kostoev R., Simonov M., Pissarenko D., Orlova D., Koroteev D. (2022). End-to-end neural network approach to 3D reservoir simulation and adaptation // Journal of Petroleum Science and Engineering, 208, 109332. https://doi.org/10.1016/j.petrol.2021.109332
Kosyakov, V. P. (2020). Structural and Parametric Identification of an Aquifer Model for an Oil Reservoir // Lobachevskii Journal of Mathematics, 41(7), 1242-1247. — DOI 10.1134/S1995080220070239. — EDN GLMSUQ.
SciPy documentation. SciPy.org. Retrieved January 27, 2025, from https://docs.scipy.org/doc/scipy/index.html#
Scikit-learn documentation. scikit-learn.org. Retrieved January 27, 2025, from https://scikit-learn.org/stable/#
Temirchev P., Simonov M., Kostoev R., Burnaev E., Oseledets I., Akhmetov A., Margarit A., Sitnikov A., Koroteev D. (2020). Deep neural networks predicting oil movement in a development unit // Journal of Petroleum Science and Engineering, 184, 106513. https://doi.org/10.1016/j.petrol.2019.106513
Xiaoyong Wen, Jing Yang, Shaoyang Geng, Ke Li. (2019). Study on new method for evaluating reservoir formation pressure by wellhead pressure // IOP Conference Series: Earth and Environmental Science. Vol. 384. № 012037. DOI: 10.1088/1755-1315/384/1/012037
Zhao, H., Kang, Z., Zhang, X., Sun, H., Cao, L., & Reynolds, A.C. (2015). INSIM: A Data-Driven Model for History Matching and Prediction for Waterflooding Monitoring and Management with a Field Application. Annual Simulation Symposium.
