Abstract
The use of upscaled models is attractive in many-query applications that require a large number of simulation runs, such as uncertainty quantification and optimization. Highly coarsened models often display error in output quantities of interest, e.g., phase production and injection rates, so the direct use of these results for quantitative evaluations and decision making may not be appropriate. In this work, we introduce a machine-learning-based post-processing framework for modeling the error in coarse-model results in the context of uncertainty quantification. Coarse-scale models are constructed using an accurate global single-phase transmissibility upscaling procedure. The framework entails the use of high-dimensional regression (random forest in this work) to model error based on a number of error indicators or features. Many of these features are derived from approximations of the subgrid effects neglected in the coarse-scale saturation equation. These features are identified through volume averaging, and they are generated by solving a fine-scale saturation equation with a constant-in-time velocity field. Our approach eliminates the need for the user to hand-design a small number of informative (relevant) features. The training step requires the simulation of some number of fine and coarse models (in this work we perform either 10 or 30 training simulations), followed by construction of a regression model for each well. Classification is also applied for production wells. The methodology then provides a correction at each time step, and for each well, in the phase production and injection rates. Results are presented for two- and three-dimensional oil–water systems. The corrected coarse-scale solutions show significantly better accuracy than the uncorrected solutions, both in terms of realization-by-realization predictions for oil and water production rates, and for statistical quantities important for uncertainty quantification, such as P10, P50, and P90 predictions.
Similar content being viewed by others
References
Aliyev, E., Durlofsky, L.J.: Multilevel field development optimization under uncertainty using a sequence of upscaled models. Math. Geosci. 49(3), 307–339 (2017). https://doi.org/10.1007/s11004-016-9643-0
Arnold, D., Demyanov, V., Christie, M., Bakay, A., Gopa, K.: Optimisation of decision making under uncertainty throughout field lifetime: A fractured reservoir example. Comput. Geosci. 95, 123–139 (2016)
Bakay, A., Demyanov, V., Arnold, D.: Uncertainty quantification in fractured reservoirs based on outcrop modelling from northeast Brazil. In: 7th EAGE international conference and exhibition (2016)
Bardy, G., Biver, P.: Sorting reservoir models according to flow criteria: A methodology, using fast marching methods and multi-dimensional scaling. In: Mathematics of Planet Earth: Proceedings of the 15th Annual Conference of the International Association for Math. Geosci., pp. 643–646. Springer. https://doi.org/10.1007/978-3-642-32408-6_140 (2014)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Breiman, L., Cutler, A., Liaw, A., Wiener, M.: Package random forest version 4.6–12. https://cran.r-project.org/web/packages/randomForest/randomForest.pdf (2015)
Cardoso, M., Durlofsky, L.J.: Linearized reduced-order models for subsurface flow simulation. J. Comput. Phys. 229(3), 681–700 (2010)
Chen, Y., Durlofsky, L.J.: Ensemble-level upscaling for efficient estimation of fine-scale production statistics. SPE J. 13(4), 400–411 (2008)
Chen, Y., Durlofsky, L.J., Gerritsen, M., Wen, X.H.: A coupled local–global upscaling approach for simulating flow in highly heterogeneous formations. Adv. Water Resour. 26(10), 1041–1060 (2003)
Chen, Y., Mallison, B.T., Durlofsky, L.J.: Nonlinear two-point flux approximation for modeling full-tensor effects in subsurface flow simulations. Comput. Geosci. 12(3), 317–335 (2008)
Chen, Y., Park, K., Durlofsky, L.J.: Statistical assignment of upscaled flow functions for an ensemble of geological models. Comput. Geosci. 15(1), 35–51 (2011)
Drohmann, M., Carlberg, K.: The ROMES method for statistical modeling of reduced-order-model error. SIAM/ASA J. Uncertain. Quantif. 3(1), 116–145 (2015)
Durlofsky, L.J.: Coarse scale models of two phase flow in heterogeneous reservoirs: Volume averaged equations and their relationship to existing upscaling techniques. Comput. Geosci. 2(2), 73–92 (1998)
Durlofsky, L.J.: Upscaling and gridding of fine scale geological models for flow simulation. In: 8th International Forum on Reservoir Simulation (2005)
Durlofsky, L.J., Chen, Y.: Uncertainty quantification for subsurface flow problems using coarse-scale models. In: Numerical Analysis of Multiscale Problems, pp. 163–202. Springer (2012)
Efendiev, Y., Datta-Gupta, A., Ma, X., Mallick, B.: Efficient sampling techniques for uncertainty quantification in history matching using nonlinear error models and ensemble level upscaling techniques. Water Resources Research 45(11) (2009)
Efendiev, Y.R., Durlofsky, L.J.: A generalized convection-diffusion model for subgrid transport in porous media. Multiscale Model. Simul. 1(3), 504–526 (2003)
Efendiev, Y.R., Durlofsky, L.J.: Accurate subgrid models for two-phase flow in heterogeneous reservoirs. SPE J. 9(2), 219–226 (2004)
Floris, F., Bush, M., Cuypers, M., Roggero, F., Syversveen, A.R.: Methods for quantifying the uncertainty of production forecasts: A comparative study. Pet. Geosci. 7(S), S87—S96 (2001)
Glimm, J., Hou, S., Lee, Y., Sharp, D., Ye, K.: Solution error models for uncertainty quantification. Contemp. Math. 327, 115–140 (2003)
Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157–1182 (2003)
Hastie, T., Tibshirani, R., Friedman, J., Franklin, J.: The elements of statistical learning: Data mining, Inference, and prediction, vol. 27. Springer-Verlag, New York (2005)
He, J., Durlofsky, L.J.: Constraint reduction procedures for reduced-order subsurface flow models based on POD-TPWL. Int. J. Numer. Methods Eng. 103(1), 1–30 (2015)
James, G., Witten, D., Hastie, T., Tibshirani, R.: An introduction to statistical learning, vol. 6. Springer, New York (2013)
Josset, L., Ginsbourger, D., Lunati, I.: Functional error modeling for uncertainty quantification in hydrogeology. Water Resour. Res. 51(2), 1050–1068 (2015)
Khodabakhshi, M., Jafarpour, B., King, M.J.: Field applications of a multi-scale multi-physics history matching approach. In: SPE Reservoir Simulation Symposium, SPE 173239-MS (2015)
Kovscek, A., Wang, Y.: Geologic storage of carbon dioxide and enhanced oil recovery. I. Uncertainty quantification employing a streamline based proxy for reservoir flow simulation. Energy Convers. Manag. 46(11), 1920–1940 (2005)
Krogstad, S., Lie, K.A., Møyner, O., Nilsen, H.M., Raynaud, X., Skaflestad, B.: MRST-AD–An open-source framework for rapid prototyping and evaluation of reservoir simulation problems. In: SPE Reservoir Simulation Symposium, SPE 173317-MS (2015)
Krogstad, S., Raynaud, X., Nilsen, H.M.: Reservoir management optimization using well-specific upscaling and control switching. Comput. Geosci. 20(3), 695–706 (2016)
Li, H., Durlofsky, L.J.: Ensemble level upscaling for compositional flow simulation. Comput. Geosci. 20 (3), 525–540 (2016)
Li, H., Durlofsky, L.J.: Local–global upscaling for compositional subsurface flow simulation. Transp. Porous Media 111(3), 701–730 (2016)
Lie, K.A., Krogstad, S., Ligaarden, I.S., Natvig, J.R., Nilsen, H.M., Skaflestad, B.: Open-source MATLAB implementation of consistent discretisations on complex grids. Comput. Geosci. 16(2), 297–322 (2012)
Lødøen, O.P.: Bayesian calibration of reservoir models using a coarse-scale reservoir simulator in the prior specification. In: EAGE Conference on Petroleum Geostatistics (2007)
Lødøen, O.P., Omre, H.: Scale-corrected ensemble Kalman filtering applied to production-history conditioning in reservoir evaluation. SPE J. 13(2), 177–194 (2008)
Lødøen, O.P., Omre, H., Durlofsky, L.J., Chen, Y.: Assessment of uncertainty in reservoir production forecasts using upscaled flow models. In: Geostatistics Banff, pp. 713–722. Springer (2005)
Ma, X., Al-Harbi, M., Datta-Gupta, A., Efendiev, Y.: An efficient two-stage sampling method for uncertainty quantification in history matching geological models. SPE J. 13(1), 77–87 (2008)
Møyner, O., Krogstad, S., Lie, K.A.: The application of flow diagnostics for reservoir management. SPE J. 20(2), 306–323 (2015)
Ng, L.W.T., Eldred, M.: Multifidelity uncertainty quantification using non-intrusive polynomial chaos and stochastic collocation. In: 14th AIAA Non-Deterministic Approaches Conference, vol. 43 (2012)
Omre, H., Lødøen, O.P.: Improved production forecasts and history matching using approximate fluid-flow simulators. SPE J. 9(3), 339–351 (2004)
Peaceman, D.W.: Interpretation of well-block pressures in numerical reservoir simulation with nonsquare grid blocks and anisotropic permeability. SPE J. 23(3), 531–543 (1983)
Remy, N., Boucher, A., Wu, J.: Applied geostatistics with SGeMS: A user’s guide. Cambridge University Press, New York (2009)
Salehi, A., Voskov, D., Tchelepi, H.: Thermodynamically consistent transport coefficients for upscaling of compositional processes. In: SPE Reservoir Simulation Symposium, SPE 163576-MS (2013)
Scheidt, C., Caers, J.: Representing spatial uncertainty using distances and kernels. Math. Geosci. 41(4), 397–419 (2009)
Scheidt, C., Caers, J.: Uncertainty quantification in reservoir performance using distances and kernel methods–application to a west Africa deepwater turbidite reservoir. SPE J. 14(4), 680–692 (2009)
Scheidt, C., Caers, J., Chen, Y., Durlofsky, L.J.: A multi-resolution workflow to generate high-resolution models constrained to dynamic data. Comput. Geosci. 15(3), 545–563 (2011)
Shahvali, M., Mallison, B., Wei, K., Gross, H.: An alternative to streamlines for flow diagnostics on structured and unstructured grids. SPE J. 17(3), 768–778 (2012)
Shirangi, M.G., Durlofsky, L.J.: A general method to select representative models for decision making and optimization under uncertainty. Comput. Geosci. 96, 109–123 (2016)
Shook, G.M., Mitchell, K.M.: A robust measure of heterogeneity for ranking earth models: The F-PHI curve and dynamic Lorenz coefficient. In: SPE Annual Technical Conference and Exhibition, SPE 124625-MS (2009)
Strebelle, S.: Conditional simulation of complex geological structures using multiple-point statistics. Math. Geol. 34(1), 1–21 (2002)
Suzuki, S., Caers, J.K.: History matching with an uncertain geological scenario. In: SPE Annual Technical Conference and Exhibition, SPE 102154-MS (2006)
Trehan, S.: Surrogate modeling for subsurface flow: A new reduced-order model and error estimation procedures. Ph.D. thesis, Stanford University (2016)
Trehan, S., Carlberg, K.T., Durlofsky, L.J.: Error modeling for surrogates of dynamical systems using machine learning. Int. J. Numer. Methods Eng. 112(12), 1801–1827 (2017). https://doi.org/10.1002/nme.5583
Trehan, S., Durlofsky, L.J.: Trajectory piecewise quadratic reduced-order model for subsurface flow, with application to PDE-constrained optimization. J. Comput. Phys. 326, 446–473 (2016)
Vo, H.X., Durlofsky, L.J.: Data assimilation and uncertainty assessment for complex geological models using a new PCA-based parameterization. Comput. Geosci. 19(4), 747–767 (2015)
Zhang, P., Pickup, G.E., Christie, M.A.: A new practical method for upscaling in highly heterogeneous reservoir models. SPE J. 13(1), 68–76 (2008)
Acknowledgments
We thank the sponsors of the Stanford Smart Fields Consortium for financial support. We are grateful to Hai X. Vo for providing the channelized geological models used in this study, and to Olav Møyner for his support with MRST. We also thank Stanford’s Center for Computational Earth & Environmental Science for providing computational resources.
Author information
Authors and Affiliations
Corresponding author
Appendix: Random-forest regression
Appendix: Random-forest regression
Random forest is a decision-tree-based supervised statistical technique used here to construct both the classification and regression models from the EMML training dataset. We provide a succinct description here – see [5] for more details. A single decision tree can be used to recursively segment the domain of the EMML training dataset in the feature space, as shown in Fig. 22. Segmentation is achieved by minimizing the following expression in a top-down greedy approach:
Here, R1(j, s) = {f | fj < s} and R2(j, s) = {f | fj ≥ s} denote the feature-space regions as shown in Fig. 22, where j ∈{1,…,Nf} is the feature index and \(s\in \mathbb {R}^{}\) is the cut-point that segments the domain, and \(\hat { \delta }_{R_{k}} \in \mathbb {R}^{},\ k = 1,2\) denotes the mean value of the error for all of the training samples in Rk. The recursive segmentation enables the nonlinear interactions between the features to be captured. Methods of this type are known as tree-based because the recursive segmentation can be interpreted as a decision tree.
Single decision trees, however, tend to overfit the data. As a result the classification or regression model may suffer from low bias and high variance. To avoid this problem, in the random forest procedure we construct an ensemble of decision trees to improve prediction accuracy. This is accomplished by first selecting a random subsample of the EMML training dataset from the overall set. The subsamples are drawn with replacement (bootstrapping) such that the size of the new set is the same as that of the original set. Then, when constructing each decision tree, at any node of the tree, random forest selects a random subset of features from all possible features, and then segments the data based on this subset. This entails solving Eq. 28 using the subset of features. As a result of these treatments, random forest leads to reduction in the variance without a corresponding increase in the bias. The random forest implementation used in this work is provided in [6].
Rights and permissions
About this article
Cite this article
Trehan, S., Durlofsky, L.J. Machine-learning-based modeling of coarse-scale error, with application to uncertainty quantification. Comput Geosci 22, 1093–1113 (2018). https://doi.org/10.1007/s10596-018-9740-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10596-018-9740-x