georesГеоресурсыGeoresources1608-50431608-5078Georesursy LLC10.18599/grs.2023.4.4geores-9Research ArticleСТАТЬИRESEARCH ARTICLESПостроение адаптивных гидродинамических моделей пониженного порядка на основе метода POD-DEIMConstruction of adaptive reduced-order reservoir models based on POD‑DEIM approachВолосковД. С.VoloskovD. S.

Дмитрий Сергеевич Волосков – инженер-исследователь

121025, Москва, Большой бульвар 30, стр. 1

Dmitry S. Voloskov – Research Engineer

30, build. 1, Moscow, 121025

dmitry.voloskov@skoltech.ruКоротеевД. А.KoroteevD. A.

Дмитрий Анатольевич Коротеев – кандидат физ.-мат. наук, профессор

121025, Москва, Большой бульвар, 30, стр. 1 

Dmitry A. Koroteev – PhD, Professor

30, build. 1, Moscow, 121025

Сколковский институт науки и технологийРоссияSkolkovo Institute of Science and TechnologyRussian Federation2023280320242546981Copyright © Волосков Д.С., Коротеев Д.А., 20242024Волосков Д.С., Коротеев Д.А.Voloskov D.S., Koroteev D.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.geors.ru/jour/article/view/9

Предложен метод построения адаптивных гидродинамических моделей пониженного порядка POD-DEIM для задач оптимизации разработки и адаптации к историческим данным, основанный на адаптации базисов ортогональных разложений к изменяющейся конфигурации модели. Метод предполагает использование информации, содержащейся в базисах исходной модели, и дополнение их новыми компонентами вместо построения последующих моделей с нуля. Применение адаптации базисов позволяет существенно снизить вычислительные затраты на построение моделей пониженного порядка и открывает возможность применения подобных моделей для задач, требующих множественных расчетов моделей с различными конфигурациями. В работе реализована модель POD-DEIM для задачи двухфазной фильтрации и рассмотрены примеры адаптации данной модели к изменениям конфигурации скважин и геологических свойств коллектора. Предложен обобщенный подход применения моделей POD-DEIM в комбинации с методом адаптации базисов для решения оптимизационных задач, таких как оптимизация разработки, выбор оптимальных расположения, геометрии и режима скважин, а также адаптация гидродинамических моделей к историческим данным.

This paper introduces a method for constructing adaptive reduced-order reservoir simulation models based on the POD-DEIM approach for field development optimization and assisted history matching problems. The approach is based on adapting the orthogonal decompositions bases to the varying model configuration. The method utilizes information contained in the bases of the original model and supplements them with new components instead of constructing a new model from scratch. Adapting the bases significantly reduces the computational costs of building reduced-order models and allows the application of such models to tasks requiring multiple simulations with different configurations. The paper presents an implementation of the POD-DEIM model for a two-phase flow problem and discusses examples of adapting this model to changes in well configuration and geological properties of the reservoir. We propose a generalized approach using POD-DEIM models in combination with the bases adaptation technique to solve optimization problems, such as field development optimization, selection of the optimal well locations, geometries, and well regimes, as well as history matching.

гидродинамическое моделированиемодели пониженного порядкаоптимизация разработкиадаптация к историческим даннымreservoir simulationreduced order modellingfield development optimizationassisted history matchingРабота поддержана Министерством науки и высшего образования Российской Федерации по соглашению № 075-10-2022-011 в рамках программы развития НЦМУThis work was supported by the Ministry of Science and Higher Education of the Russian Federation under agreement No. 075-10-2022-011 within the framework of the development program for a world-class Research Center.ReferencesCardoso M. A. (2010). Use of Reduced-Order Modeling Procedures for Production Optimization. SPE Journal, 15(2010), pp. 426–435. https://doi.org/10.2118/119057-PACardoso M. A. (2010). Use of Reduced-Order Modeling Procedures for Production Optimization. SPE Journal, 15(2010), pp. 426–435. https://doi.org/10.2118/119057-PAChaturantabut S., Sorensen D.C. (2010). Nonlinear Model Reduction via Discrete Empirical Interpolation. SIAM Journal on Scientific Computing, 32(5), pp. 2737–2764. https://doi.org/10.1137/090766498Chaturantabut S., Sorensen D.C. (2010). Nonlinear Model Reduction via Discrete Empirical Interpolation. SIAM Journal on Scientific Computing, 32(5), pp. 2737–2764. https://doi.org/10.1137/090766498Efendiev Y., Gildin E., Yang Y. (2016). Online Adaptive Local-Global Model Reduction for Flows in Heterogeneous Porous Media. Computation, 4(2), 22. https://doi.org/10.3390/computation4020022Efendiev Y., Gildin E., Yang Y. (2016). Online Adaptive Local-Global Model Reduction for Flows in Heterogeneous Porous Media. Computation, 4(2), 22. https://doi.org/10.3390/computation4020022Fanchi J. R. (2018). Principles of applied reservoir simulation (Fourth edition). Gulf Professional Publishing, Elsevier. https://doi.org/10.1016/C2017-0-00352-XFanchi J. R. (2018). Principles of applied reservoir simulation (Fourth edition). Gulf Professional Publishing, Elsevier. https://doi.org/10.1016/ C2017-0-00352-XFraces C.G., Papaioannou A., Tchelepi H. (2020). Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem. ArXiv:2001.05172. http://arxiv.org/abs/2001.05172Fraces C.G., Papaioannou A., Tchelepi H. (2020). Physics Informed Deep Learning for Transport in Porous Media. Buckley Leverett Problem. ArXiv:2001.05172. http://arxiv.org/abs/2001.05172Gasmi C. F., Tchelepi H. (2021). Physics Informed Deep Learning for Flow and Transport in Porous Media. ArXiv:2104.02629. http://arxiv.org/abs/2104.02629Gasmi C. F., Tchelepi H. (2021). Physics Informed Deep Learning for Flow and Transport in Porous Media. ArXiv:2104.02629. http://arxiv.org/abs/2104.02629He J., Sætrom J., Durlofsky L.J. (2011). Enhanced linearized reducedorder models for subsurface flow simulation. Journal of Computational Physics, 230(23), pp. 8313–8341. https://doi.org/10.1016/j.jcp.2011.06.007He J., Sætrom J., Durlofsky L.J. (2011). Enhanced linearized reducedorder models for subsurface flow simulation. Journal of Computational Physics, 230(23), pp. 8313–8341. https://doi.org/10.1016/j.jcp.2011.06.007Illarionov E., Temirchev P., Voloskov D., Kostoev R., Simonov M., Pissarenko D., Orlov 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.2021.109332Illarionov E., Temirchev P., Voloskov D., Kostoev R., Simonov M., Pissarenko D., Orlov 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.2021.109332Jansen J.D., Durlofsky L.J. (2017). Use of reduced-order models in well control optimization. Optimization and Engineering, 18(1), pp. 105–132. https://doi.org/10.1007/s11081-016-9313-6Jansen J.D., Durlofsky L.J. (2017). Use of reduced-order models in well control optimization. Optimization and Engineering, 18(1), pp. 105–132. https://doi.org/10.1007/s11081-016-9313-6Jin Z.L., Liu Y., Durlofsky L.J. (2020). Deep-learning-based surrogate model for reservoir simulation with time-varying well controls. Journal of Petroleum Science and Engineering, 107273. https://doi.org/10.1016/j.petrol.2020.107273Jin Z.L., Liu Y., Durlofsky L.J. (2020). Deep-learning-based surrogate model for reservoir simulation with time-varying well controls. Journal of Petroleum Science and Engineering, 107273. https://doi.org/10.1016/j.petrol.2020.107273Kani J.N., Elsheikh A.H. (2017). DR-RNN: A deep residual recurrent neural network for model reduction. ArXiv:1709.00939. http://arxiv.org/abs/1709.00939Kani J.N., Elsheikh A.H. (2017). DR-RNN: A deep residual recurrent neural network for model reduction. ArXiv:1709.00939. http://arxiv.org/abs/1709.00939Kani J.N., Elsheikh A.H. (2018). Reduced-Order Modeling of Subsurface Multi-phase Flow Models Using Deep Residual Recurrent Neural Networks. Transport in Porous Media, (126), pp. 713–741 https://doi.org/10.1007/s11242-018-1170-7Kani J.N., Elsheikh A.H. (2018). Reduced-Order Modeling of Subsurface Multi-phase Flow Models Using Deep Residual Recurrent Neural Networks. Transport in Porous Media, (126), pp. 713–741 https://doi.org/10.1007/s11242-018-1170-7Kunisch K., Volkwein S. (2003). Galerkin Proper Orthogonal Decomposition Methods for a General Equation in Fluid Dynamics. SIAM Journal on Numerical Analysis, 40(2), pp. 492–515.Kunisch K., Volkwein S. (2003). Galerkin Proper Orthogonal Decomposition Methods for a General Equation in Fluid Dynamics. SIAM Journal on Numerical Analysis, 40(2), pp. 492–515.Monteagudo J.E.P., Firoozabadi A. (2004). Control-volume method for numerical simulation of two-phase immiscible flow in two- and threedimensional discrete-fractured media. Water Resources Research, 40(7). https://doi.org/10.1029/2003WR002996Monteagudo J.E.P., Firoozabadi A. (2004). Control-volume method for numerical simulation of two-phase immiscible flow in two- and threedimensional discrete-fractured media. Water Resources Research, 40(7). https://doi.org/10.1029/2003WR002996Pacheco T.B., Silva A.F.C.D., Maliska C. (2017). Comparison of impes, sequential, and fully implicit formulations for two-phase flow in porous media with the element-based finite volume method. Rewienski M., White J. (2003). A trajectory piecewise-linear approach to model order reduction and fast simulation of nonlinear circuits and micromachined devices. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 22(2), pp. 155–170. https://doi.org/10.1109/TCAD.2002.806601Pacheco T.B., Silva A.F.C.D., Maliska C. (2017). Comparison of impes, sequential, and fully implicit formulations for two-phase flow in porous media with the element-based finite volume method. Rewienski M., White J. (2003). A trajectory piecewise-linear approach to model order reduction and fast simulation of nonlinear circuits and micromachined devices. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 22(2), pp. 155–170. https://doi.org/10.1109/TCAD.2002.806601Tan X., Gildin E., Florez H., Trehan S., Yang Y., Hoda N. (2019). Trajectory-based DEIM (TDEIM) model reduction applied to reservoir simulation. Computational Geosciences, 23(1), pp. 35–53. https://doi.org/10.1007/s10596-018-9782-0Tan X., Gildin E., Florez H., Trehan S., Yang Y., Hoda N. (2019). Trajectory-based DEIM (TDEIM) model reduction applied to reservoir simulation. Computational Geosciences, 23(1), pp. 35–53. https://doi.org/10.1007/s10596-018-9782-0Temirchev 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.2019.106513Temirchev 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.2019.106513Trehan S., Durlofsky L.J. (2016). Trajectory piecewise quadratic reduced-order model for subsurface flow, with application to PDE-constrained optimization. Journal of Computational Physics, 326, pp. 446–473. https://doi.org/10.1016/j.jcp.2016.08.032Trehan S., Durlofsky L.J. (2016). Trajectory piecewise quadratic reduced-order model for subsurface flow, with application to PDE-constrained optimization. Journal of Computational Physics, 326, pp. 446–473. https://doi.org/10.1016/j.jcp.2016.08.032Voloskov D., Pissarenko D. (2021). Adaptive POD-Galerkin Technique for Reservoir Simulation and Optimization. Mathematical Geosciences, 53, pp. 1951–1975. https://doi.org/10.1007/s11004-021-09958-6Voloskov D., Pissarenko D. (2021). Adaptive POD-Galerkin Technique for Reservoir Simulation and Optimization. Mathematical Geosciences, 53, pp. 1951–1975. https://doi.org/10.1007/s11004-021-09958-6Yang Y., Ghasemi M., Gildin E., Efendiev Y., Calo V. (2016). Fast Multiscale Reservoir Simulations With POD-DEIM Model Reduction. SPE Journal, 21(06), pp. 2141–2154. https://doi.org/10.2118/173271-PAYang Y., Ghasemi M., Gildin E., Efendiev Y., Calo V. (2016). Fast Multiscale Reservoir Simulations With POD-DEIM Model Reduction. SPE Journal, 21(06), pp. 2141–2154. https://doi.org/10.2118/173271-PAYoung L. C. (1981). A Finite-Element Method for Reservoir Simulation. Society of Petroleum Engineers Journal, 21(01), pp. 115–128. https://doi.org/10.2118/7413-PAYoung L. C. (1981). A Finite-Element Method for Reservoir Simulation. Society of Petroleum Engineers Journal, 21(01), pp. 115–128. https://doi.org/10.2118/7413-PA

The authors declare that there are no conflicts of interest present.