Abstract
Numerical models representing geological reservoirs can be used to forecast production and help engineers to design optimal development plans. These models should be as representative as possible of the true dynamic behavior and reproduce available static and dynamic data. However, identifying models constrained to production data can be very challenging and time consuming. Machine learning techniques can be considered to mimic and replace the fluid flow simulator in the process. However, the benefit of these approaches strongly depends on the simulation time required to train reliable predictors. Previous studies highlighted the potential of the multi-fidelity approach rooted in cokriging to efficiently provide accurate estimations of fluid flow simulator outputs. This technique consists in combining simulation results obtained on several levels of resolution for the reservoir model to predict the output properties on the finest level (the most accurate one). The degraded levels can correspond for instance to a coarser discretization in space or time, or to less complex physics. The idea behind is to take advantage of the coarse level low-cost information to limit the total simulation time required to train the meta-models. In this paper, we propose a new sequential design strategy for iteratively and automatically training (kriging and) cokriging based meta-models. As highlighted on two synthetic cases, this approach makes it possible to identify training sets leading to accurate estimations for the error between measured and simulated production data (objective function) while requiring limited simulation times.
Similar content being viewed by others
Data availability
The original PUNQ-S3 data set used to build the first test case considered in this paper is available online: http://www.imperial.ac.uk/earth-science/research/research-groups/perm/standard-models/eclipse-dataset. The original Brugge data set used to build the second test case was provided by TNO. It can be requested to TNO via www.isapp2.com.
References
Busby, D.: Hierarchical adaptive experimental design for Gaussian process emulators. Reliab. Eng. Syst. Safe. 94(7), 1183–1193 (2009). https://doi.org/10.1016/j.ress.2008.07.007
Cardwell Jr., W.T., Parsons, R.L.: Average permeabilities of heterogeneous oil sands. Soc. Pet. Eng. 160, 34–42 (1945). https://doi.org/10.2118/945034-G
Douarche, F., Da Veiga, S., Feraille, M., Enchéry, G., Touzani, S., Barsalou, R.: Sensitivity analysis and optimization of surfactant-polymer flooding under uncertainties. Oil Gas Sci. Technol. – Rev. d’IFP Energies Nouvelles. 69, 603–617 (2014). https://doi.org/10.2516/ogst/2013166
Dubrule, O.: Cross validation of kriging in a unique neighborhood. J. Int. Assoc. Math. Geol. 15(6), 687–699 (1983). https://doi.org/10.1007/BF01033232
Feraille, M., Marrel, A.: Prediction under uncertainty on a mature field. Oil Gas Sci. Technol. – Rev. IFP Energies Nouvelles. 67(2), 193–206 (2012). https://doi.org/10.2516/ogst/2011172
Floris, F.J.T., Bush, M.D., Cuypers, M., Roggero, F., Syversveen, A.-R.: Methods for quantifying the uncertainty of production forecasts: a comparative study. Pet. Geosci. 7, S87–S96 (2001). https://doi.org/10.1144/petgeo.7.S.S87
Forrester, A.I.J., Keane, A.J.: Recent advances in surrogate-based optimization. Prog. Aerosp. Sci. 45, 50–79 (2009). https://doi.org/10.1016/j.paerosci.2008.11.001
Jones, D., Schonlau, M., Welch, W.: Efficient global optimization of expensive black-box functions. J. Glob. Optim. 13(4), 455–492 (1998). https://doi.org/10.1023/A:1008306431147
Journel, A.G., Deutsch, C.V.: GSLIB Geostatistical Software Library and Users Guide, 2nd edn. Oxford University Press, New York (1998)
Kennedy, M., O’Hagan, A.: Predicting the output from a complex computer code when fast approximations are available. Biometrika. 87, 1–13 (2000). https://doi.org/10.1093/biomet/87.1.1
Le Gratiet, L.: Bayesian analysis of hierarchical multifidelity codes. SIAM/ASA J. Uncertain. Quantif. 1(1), 244–269 (2013). https://doi.org/10.1137/120884122
Le Gratiet, L.: MuFiCokriging: multi-fidelity cokriging models. R package version 1.2 (2014) https://cran.r-project.org/web/packages/MuFiCokriging/index.html
Le Gratiet, L., Cannamela, C.: Cokriging-based sequential design strategies using fast cross-validation techniques for multi-Fidelity computer codes. Technometrics. 57(3), 418–427 (2015). https://doi.org/10.1080/00401706
Le Gratiet, L., Garnier, J.: Recursive cokriging model for design of computer experiments with multiple levels of Fidelity. Int. J. Uncertain. Quantif. 4(5), 365–386 (2014). https://doi.org/10.1615/Int.J.UncertaintyQuantification.2014006914
Le Ravalec, M.: Optimizing well placement with quality maps derived from multi-fidelity meta-models. Paper SPE 154416 presented at the EAGE Annual Conference and Exhibition incorporating SPE Europec, Copenhagen, Denmark (2012) https://doi.org/10.2118/154416-MS
Le Ravalec, M., Noetinger, B., Hu, L.: The FFT moving average (FFT-MA) generator: an efficient numerical method for generating and conditioning gaussian simulations. Math. Geol. 32, 701–723 (2000). https://doi.org/10.1023/A:1007542406333
Le Ravalec, M., Da Veiga, S., Derfoul, R., Enchéry, G., Gervais, V., Roggero, F.: Integrating data of different types and different supports into reservoir models. Oil Gas Sci. Technol. 67(5), 823–840 (2012). https://doi.org/10.2516/ogst/2012024
Loeve, M.: Probability Theory, Vol. I–II. Springer, New York (1978)
Mardia, K.V., Marshall, R.J.: Maximum likelihood estimation of models for residual covariance in spatial regression. Biometrika. 71(1), 135–146 (1984)
Marrel, A., Perot, N., Mottet, C.: Development of a surrogate model and sensitivity analysis for spatio-temporal numerical simulators. Stoch. Env. Res. Risk A. 29(3), 959–974 (2015). https://doi.org/10.1007/s00477-014-0927-y
Matérn, B.: Spatial Variation. Springer, New York (1986)
O’Hagan, A.: A Markov Property for Covariance structures. University of Nottingham (1998)
Peters, L., Arts, R., Brouwer, G., Geel, C., Cullick, S., Lorentzen, R.J., Chen, Y., Dunlop, N., Vossepoel, F.C., Xu, R., et al.: Results of the brugge benchmark study for flooding optimization and history matching. SPE Reserv. Eval. Eng. 13(03), 391–405 (2010). https://doi.org/10.2118/119094-PA
Peters, E., Chen, Y., Leeuwenburgh, O., Oliver, D.: Extended Brugge benchmark case for history matching and water flooding optimization. Comput. Geosci. 50, 16–24 (2013). https://doi.org/10.1016/j.cageo.2012.07.018
Picheny, V., Ginsbourger, D., Roustant, O., Haftka, R., Kim, N.-H.: Adaptive designs of experiments for accurate approximation of a target region. J. Mech. Des. 132(7), 071008-1–071008-9 (2010). https://doi.org/10.1115/1.4001873
Roustant, O., Ginsbourger, D., Deville, Y.: Dicekriging, DiceOptim: two R packages for the analysis of computer experiments by kriging-based metamodeling and optimization. J. Stat. Softw. 51(1), 1–55 (2012). https://doi.org/10.18637/jss.v051.i01
Sacks, J., Welch, W.J., Mitchell, T.J., Wynn, H.P.: Design and analysis of computer experiments. Stat. Sci. 4, 409–423 (1989). https://doi.org/10.1214/ss/1177012413
Santner, T.J., Williams, B.J., Notz, W.: The Design and Analysis of Computer Experiments. Springer-Verlab, New York (2003)
Thenon, A., Gervais, V., Ravalec, M.L.: Multi-fidelity meta-modeling for reservoir engineering - application to history matching. Comput. Geosci. 20, 1231–1250 (2016). https://doi.org/10.1007/s10596-016-9587-y
Xiong, S., Qian, P.Z.G., Wu, C.F.J.: Sequential design and analysis of high-accuracy and low-accuracy computer codes. Technometrics. 55(1), 37–46 (2012). https://doi.org/10.1080/00401706.2012.723572
Yeten, B., Castellini, A., Guyaguler, B., Chen, W.H.: A Comparison Study on Experimental Design and Response Surface Methodologies. In SPE-93347-MS. SPE: Society of Petroleum Engineers (2005). https://doi.org/10.2118/93347-MS
Zubarev, D.I.: Pros and Cons of Applying Proxy-Models as a Substitute for Full Reservoir Simulations. In SPE-124815-MS. SPE: Society of Petroleum Engineers (2009). https://doi.org/10.2118/124815-MS
Acknowledgments
The authors thank TNO for providing the Brugge data set.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
Authors declare they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Author A. Thenon is now with Modis.
Rights and permissions
About this article
Cite this article
Thenon, A., Gervais, V. & Le Ravalec, M. Sequential design strategy for kriging and cokriging-based machine learning in the context of reservoir history-matching. Comput Geosci 26, 1101–1118 (2022). https://doi.org/10.1007/s10596-022-10147-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-022-10147-5