Abstract
We propose to use a conventional simulator, formulated on the topology of a coarse volumetric 3D grid, as a data-driven network model that seeks to reproduce observed and predict future well responses. The conceptual difference from standard history matching is that the tunable network parameters are calibrated freely without regard to the physical interpretation of their calibrated values. The simplest version uses a minimal rectilinear mesh covering the assumed map outline and base/top surface of the reservoir. The resulting CGNet models fit immediately in any standard simulator and are very fast to evaluate because of the low cell count. We show that surprisingly accurate network models can be developed using grids with a few tens or hundreds of cells. Compared with similar interwell network models (e.g., Ren et al., 2019, 10.2118/193855-MS), a typical CGNet model has fewer computational cells but a richer connection graph and more tunable parameters. In our experience, CGNet models therefore calibrate better and are simpler to set up to reflect known fluid contacts, etc. For cases with poor vertical connection or internal fluid contacts, it is advantageous if the model has several horizontal layers in the network topology. We also show that starting with a good ballpark estimate of the reservoir volume is a precursor to a good calibration.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Navrátil, J., King, A., Rios, J., Kollias, G., Torrado, R., Codas, A.: Accelerating physics-based simulations using end-to-end neural network proxies: an application in oil reservoir modeling. Frontiers in Big Data 2, 33 (2019). https://doi.org/10.3389/fdata.2019.00033
Jin, Z.L., Liu, Y., Durlofsky, L.J.: Deep-learning-based surrogate model for reservoir simulation with time-varying well controls. J. Petrol. Sci. Eng. 192, 107273 (2020). https://doi.org/10.1016/j.petrol.2020.107273
Kim, J., Yang, H., Choe, J.: Robust optimization of the locations and types of multiple wells using CNN based proxy models. J. Petrol. Sci. Eng. 193, 107424 (2020). https://doi.org/10.1016/j.petrol.2020.107424
Kim, Y.D., Durlofsky, L.J.: A recurrent neural network-based proxy model for well-control optimization with nonlinear output constraints. SPE J. 26(04), 1837–1857 (2021). https://doi.org/10.2118/203980-PA
Liu, Z., Reynolds, A.C.: Gradient-enhanced support vector regression for robust life-cycle production optimization with nonlinear-state constraints. SPE J. 26(04), 1590–1613 (2021). https://doi.org/10.2118/204236-PA
Wang, N., Chang, H., Zhang, D.: Theory-guided auto-encoder for surrogate construction and inverse modeling. Comput. Methods Appl. Mech. Eng. 385(114037) (2021). https://doi.org/10.1016/j.cma.2021.114037
Zhang, K., Wang, Y., Li, G., Ma, X., Cui, S., Luo, Q., Wang, J., Yang, Y., Yao, J.: Prediction of field saturations using a fully convolutional network surrogate. SPE J. 26(04), 1824–1836 (2021). https://doi.org/10.2118/205485-PA
Zhong, Z., Sun, A.Y., Ren, B., Wang, Y.: A deep-learning-based approach for reservoir production forecast under uncertainty. SPE J. 26(03), 1314–1340 (2021). https://doi.org/10.2118/205000-PA
Lie, K.A., Krogstad, S.: Comparison of two different types of reduced graph-based reservoir models: Interwell networks (GPSNet) versus aggregated coarse-grid networks (CGNet). Geoenergy Sci. Eng. 221, 111266 (2023). https://doi.org/10.1016/j.petrol.2022.111266
Khodabakhshi, M., Jafarpour, B., King, M.J.: Field applications of a multi-scale multi-physics history matching approach. In: SPE Reserv.- Simul. Symp. (2015). https://doi.org/10.2118/173239-MS
Khodabakhshi, M., Jafarpour, B., King, M.J.: Inference of global reservoir connectivity from static pressure data with fast coarse-scale simulation models. Math. Geosci.51(5), 625–648 (2019). https://doi.org/10.1007/s11004-018-9772-8
Yousef, A.A., Lake, L.W., Jensen, J.L.: Analysis and interpretation of interwell connectivity from production and injection rate fluctuations using a capacitance model. In: SPE/DOE Symposium on Improved Oil Recovery, Tulsa, Oklahoma, USA (2006). https://doi.org/10.2118/99998-MS
Holanda, R., Gildin, E., Jensen, J., Lake, L., Kabir, C.: A state-of-the-art literature review on capacitance resistance models for reservoir characterization and performance forecasting. Energ. 11(12), 3368 (2018). https://doi.org/10.3390/en11123368
Alghamdi, A., Hiba, M., Aly, M., Awotunde, A.: A critical review of capacitance-resistance models. In: SPE Russian Petroleum Technology Conference, Virtual (2021). https://doi.org/10.2118/206555-MS
Dobbyn, A., Marsh, M.: Material balance: A powerful tool for understanding the early performance of the Schiehallion field. In: SPE Offshore Europe Oil and Gas Exhibition and Conference, Aberdeen, United Kingdom, September (2001). https://doi.org/10.2118/71819-MS
Govan, A., Primmer, T., Douglas, C., Moodie, N., Davies, M., Nieuwland, F.: Reservoir management in a deepwater subsea field–the Schiehallion experience. SPE Reservoir Evalaluation & Engineering 9(04), 382–390 (2006). https://doi.org/10.2118/96610-PA
Williams, G.J.J., Mansfield, M., MacDonald, D.G., Bush, M.D.: Topdown reservoir modelling. In: SPE Annual Technical Conference and Exhibition, Houston, Texas, September 2004 (2004). https://doi.org/10.2118/89974-MS
Zhao, H., Kang, Z., Zhang, X., Sun, H., Cao, L., Reynolds, A.C.: INSIM: A data-driven model for history matching and prediction for waterflooding monitoring and management with a field application. In: SPE Reservoir Simulation Symposium, Houston, Texas, USA, February 2015 (2015). https://doi.org/10.2118/173213-MS
Guo, Z., Reynolds, A.C., Zhao, H.: A physics-based data-driven model for history matching, prediction, and characterization of waterflooding performance. SPE J. 23(02), 367–395 (2017). https://doi.org/10.2118/182660-PA
Guo, Z., Reynolds, A.C., Zhao, H.: Waterflooding optimization with the INSIM-FT data-driven model. Comput. Geosci. 22(3), 745–761 (2018). https://doi.org/10.1007/s10596-018-9723-y
Guo, Z., Reynolds, A.C.: INSIM-FT in three-dimensions with gravity. J. Comput. Phys. 380, 143–169 (2019). https://doi.org/10.1016/j.jcp.2018.12.016
Li, Y., Onur, M.: INSIM-BHP: A physics-based data-driven reservoir model for history matching and forecasting with bottomhole pressure and production rate data under waterflooding. J. Comput. Phys. 473, 111714 (2023). https://doi.org/10.1016/j.jcp.2022.111714
Lerlertpakdee, P., Jafarpour, B., Gildin, E.: Efficient production optimization with flow-network models. SPE J. 19(06), 1083–1095 (2014). https://doi.org/10.2118/170241-PA
Lutidze, G.: StellNet – physics-based data-driven general model for closedloop reservoir management. PhD thesis, The University of Tulsa (2018)
Ren, G., He, J., Wang, Z., Younis, R.M., Wen, X.-H.: Implementation of physics-based data-driven models with a commercial simulator. In: SPE Reservoir Simulation Conference, Galveston, Texas, USA, April (2019). https://doi.org/10.2118/193855-MS
Behm, E., Asimi, M.A., Maskari, S.A., Juna, W., Klie, H., Le, D., Lutidze, G., Rastegar, R., Reynolds, A., Tathed, V., Younis, R., Zhang, Y.: Middle East steamflood field optimization demonstration project. In: Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, November 2019 (2019). https://doi.org/10.2118/197751-MS
Kiærr, A., Lødøen, O.P., Bruin, W.D., Barros, E., Leeuwenburgh, O.: Evaluation of a data-driven flow network model (FlowNet) for reservoir prediction and optimization. In: ECMOR XVII – 17th European Conference on the Mathematics of Oil Recovery (2020). https://doi.org/10.3997/2214-4609.202035099
Asimi, M.A., Qasabi, N.A., Le, D., Zhang, Y., Zhu, D., Balushi, K.A.: Expansion of data analytics for optimizing steamflood in Mukhaizna heavy oil field. In: Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, November (2021). https://doi.org/10.2118/207680-MS
Wang, Z., He, J., Milliken, W.J., Wen, X.-H.: Fast history matching and optimization using a novel physics-based data-driven model: an application to a diatomite reservoir. SPE J. 26(06), 4089–4108 (2021). https://doi.org/10.2118/200772-PA
Mamonov, A., Couet, B., Bailey, W.J., Prange, M., Djikpesse, H.A., Druskin, V.: Optimal grid coarsening: A fast proxy for large reservoir simulations. In: SPE Reservoir Characterisation and Simulation Conference and Exhibition, Abu Dhabi, UAE, October 2007 (2007). https://doi.org/10.2118/111378-MS
Sankaran, S., Sun, W.: A flow network model based on time of flight for reservoir management. In: Abu Dhabi International Petroleum Exhibition and Conference (2020). https://doi.org/10.2118/203390-MS
Guo, Z., Sankaran, S., Sun, W.: Reservoir modeling, history matching,and characterization with a reservoir graph network model. SPE Reserv. Eval. Eng. 1–13 (2023). https://doi.org/10.2118/209337-PA
Iino, A., Jung, H.Y., Onishi, T., Datta-Gupta, A.: Rapid simulation accounting for well interference in unconventional reservoirs using fast marching method. In: SPE/AAPG/SEG Unconv. Res. Technol. Conf. (2020). https://doi.org/10.15530/urtec-2020-2468
Lie, K.A.: An Introduction to Reservoir Simulation Using MATLAB/GNU Octave: User Guide for the MATLAB Reservoir Simulation Toolbox (MRST). Cambridge University Press, Cambridge, United Kingdom (2019). https://doi.org/10.1017/9781108591416
Emerick, A., Reynolds, A.: Ensemble smoother with multiple data assimilation. Comput. Geosci. 55, 3–15 (2013). https://doi.org/10.1016/j.cageo.2012.03.011
Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, New York, NY, USA (2006)
Oliver, D.S., Reynolds, A.C., Liu, N.: Inverse Theory for Petroleum Reservoir Characterization and History Matching. Cambridge University Press, Cambridge, United Kingdom (2008). https://doi.org/10.1017/CBO9780511535642
Byrd, R.H., Lu, P., Nocedal, J., Zhu, C.: A limited memory algorithm for bound constrained optimization. SIAM Journal on Scientific Computing 16(5), 1190–1208 (1995). https://doi.org/10.1137/0916069
Jansen, J.D., Fonseca, R.M., Kahrobaei, S., Siraj, M.M., Essen, G.M.V., den Hof, P.M.J.V.: The egg model - a geological ensemble for reservoir simulation. Geosci. Data J. 1(2), 192–195 (2014). https://doi.org/10.1002/gdj3.21
MRST: The MATLAB Reservoir Simulation Toolbox (MRST), version 2022a. SINTEF, Oslo, Norway. SINTEF Digital (2022). https://doi.org/10.5281/zenodo.6390187.mrst.no
Lie, K.A., Møyner, O. (eds.): Advanced Modeling with the MATLAB Reservoir Simulation Toolbox. Cambridge University Press, Cambridge, United Kingdom (2021). https://doi.org/10.1017/9781009019781
Lorentzen, R.J., Luo, X., Bhakta, T., Valestrand, R.: History matching the full Norne field model using seismic and production data. SPE J. 24(4), 1452–1467 (2019). https://doi.org/10.2118/194205-PA
Natvig, J.R., Lie, K.A.: Fast computation of multiphase flow in porous media by implicit discontinuous Galerkin schemes with optimal ordering of elements. J. Comput. Phys. 227(24), 10108–10124 (2008). https://doi.org/10.1016/j.jcp.2008.08.024
Acknowledgements
The authors acknowledge funding from the Research Council of Norway through grant no. 280950 with co-funding from Equinor Energy AS, TotalEnergies EP Norge AS, and Wintershall DEA Norge AS.
Funding
Open access funding provided by SINTEF.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests/Competing Interests
The research leading to the results reported in this manuscript received funding from the Research Council of Norway through grant no. 280950 which includes co-funding from Equinor Energy AS, TotalEnergies EP Norge AS, and Wintershall DEA Norge AS. Apart from this funding, the authors have no financial or competing interests to declare that are relevant to the content of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Lie, KA., Krogstad, S. Data-driven modelling with coarse-grid network models. Comput Geosci 28, 273–287 (2024). https://doi.org/10.1007/s10596-023-10237-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-023-10237-y