Abstract
Constructing subsurface models that accurately reproduce geological heterogeneity and their associated uncertainty is critical to many geoscience and engineering applications. For hydrocarbon reservoir modeling and forecasting, for example, spatial variability must be consistent with geological processes, geophysical measurements, and time records of fluid production measurements. Generating such subsurface models can be time-consuming; conditioning them to different types of measurements is even more computationally intensive and technically challenging. Using too many free variables can cause overfitting of the data, thereby decreasing the predictive ability of the model; high dimensionality also slows convergence during history matching of fluid production measurements. To contend with these problems, we introduce here a new machine learning approach, referred to as the stochastic pix2pix method, which parameterizes high-dimensional, stochastic reservoir models into low-dimensional Gaussian random variables in latent space. Many of the world’s significant hydrocarbon fields originate from fluvial or turbidite deposits, with sedimentary processes and spatial distribution of rock facies significantly influencing their flow behavior. Rule- or object-based methods are commonly used to model geostatistically these types of reservoirs. Here, we introduce a new and efficient machine learning-based reservoir modeling workflow capable of generating 2D fluvial reservoir models that account for the available field data and the geometries of different facies. By constraining subsurface model realizations to available geophysical and petrophysical interpretations, multiphysics inversion can be greatly accelerated, thereby requiring only production history matching. Although our models are 2D, an extension to 3D can be readily implemented through zone-by-zone (i.e., reservoir unit) modeling and conditioning. The proposed method and workflow also partially solve the common problem of machine learning methods, wherein mapping low- to high-resolution images often yield reduced spatial variability. The proposed method is an extension of conditional generative adversarial networks, in which we incorporate a novel penalty term into the loss function in order to generate various realizations honoring the same conditional data, such as structural interpretation from seismic data, and borehole measurements at key well locations. We “train” the generative model on geologically realistic, multivariate spatial models generated with a rule-based fluvial reservoir simulator. Each high-resolution training image includes five lithofacies with distinct petrophysical property trends. To evaluate the performance of the proposed method, visual inspection, indicator variograms and multiple point density function are applied to gauge how well the realizations reproduce existing patterns in the true model. A new metric, the mean categorical error, is proposed to quantify how well the realizations match the conditioning data. The proposed method correctly reproduces patterns even when the conditioning data are significantly different from those in the training set. Likewise, the method can perform continuous model modifications, meaning that the machine learning procedure effectively reproduces the migration rule of a meandering (fluvial) system.
Similar content being viewed by others
References
Alpak, F. O., Jennings, J. W., Gelderblom, P., Chen, C., Gao, G., & Du, K. (2017). A direct overparameterize and optimize method for stratigraphically consistent assisted history matching of object-based geomodels: Algorithm and field application. SPE Journal, 22(04), 1–280.
Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In ICML’17 Proceedings of the 34th International Conference on Machine Learning, (vol. 70, pp. 214–223).
Asher, M. J., Croke, B. F., Jakeman, A. J., & Peeters, L. J. (2015). A review of surrogate models and their application to groundwater modeling. Water Resources Research, 51(8), 5957–5973.
Boisvert, J. B., & Pyrcz, M. J. (2014). Conditioning 3D object based models to a large number of wells: A channel example. Mathematics of Planet Earth. https://doi.org/10.1007/978-3-642-32408-6_126.
Boisvert, J. B., Pyrcz, M. J., & Deutsch, C. V. (2006). Choosing training models and checking realizations with multiple point statistics (p. 8). NO: Centre for Computational Geostatistics.
Boisvert, J. B., Pyrcz, M. J., & Deutsch, C. V. (2007). Multiple-point statistics for training model selection. Natural Resources Research, 16(4), 313–321.
Boisvert, J. B., Pyrcz, M. J., & Deutsch, C. V. (2010). Multiple point metrics to assess categorical variable models. Natural Resources Research, 19(3), 165–175.
Caers, J. (2003). History matching under training-image-based geological model constraints. SPE Journal, 8(03), 218–226.
Chan, S., & Elsheikh, A. H. (2017). Parametrization and generation of geological models with generative adversarial networks. arXiv:1708.01810.
Cressie, N. (1985). Fitting variogram models by weighted least squares. Journal of the International Association for Mathematical Geology, 17(5), 563–586.
Cressie, N., & Hawkins, D. M. (1980). Robust estimation of the variogram: I. Journal of the International Association for Mathematical Geology, 12(2), 115–125.
Deutsch, C. V., & Journel, A. G. (1992). Geostatistical software library and user’s guide. New York: Oxford University Press.
Deutsch, C. V., & Wang, L. (1996). Hierarchical object-based stochastic modeling of fluvial reservoirs. Mathematical Geology, 28(7), 857–880.
Dupont, E., Zhang, T., Tilke, P., Liang, L., & Bailey, W. (2018). Generating realistic geology conditioned on physical measurements with generative adversarial networks. arXiv:1802.03065.
Ferguson, R. I. (1976). Disturbed periodic model for river meanders. Earth Surface Processes, 1(4), 337–347.
Ferguson, R. I., Church, M., & Weatherly, H. (2001). Fluvial aggradation in Vedder River: Testing a one-dimensional sedimentation model. Water Resources Research, 37(12), 3331–3347.
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., et al. (2014). Generative adversarial nets. Advances in Neural Information Processing Systems, 27, 2672–2680.
Gringarten, E., & Deutsch, C. V. (2001). Teacher’s aide variogram interpretation and modeling. Mathematical Geology, 33(4), 507–534.
Guin, A., Ramanathan, R., Ritzi, R. W., Jr., Dominic, D. F., Lunt, I. A., Scheibe, T. D., et al. (2010). Simulating the heterogeneity in braided channel belt deposits: 2. Examples of results and comparison to natural deposits. Water Resources Research. https://doi.org/10.1029/2009WR008112.
Haldorsen, H. H., & Lake, L. W. (1984). A new approach to shale management in field-scale models. Society of Petroleum Engineers Journal, 24(04), 447–457.
Hansen, L. K., & Salamon, P. (1990). Neural network ensembles. IEEE Transactions on Pattern Analysis and Machine Intelligence, 12(10), 993–1001.
Hassanpour, M. M., Pyrcz, M. J., & Deutsch, C. V. (2013). Improved geostatistical models of inclined heterolithic strata for McMurray Formation, Alberta, Canada. AAPG Bulletin, 97(7), 1209–1224.
Holden, L., Hauge, R., Skare, Ø., & Skorstad, A. (1998). Modeling of fluvial reservoirs with object models. Mathematical Geology, 30(5), 473–496.
Hu, L. Y. (2000). Gradual deformation and iterative calibration of Gaussian-related stochastic models. Mathematical Geology, 32(1), 87–108.
Hu, L. Y., & Chugunova, T. (2008). Multiple-point geostatistics for modeling subsurface heterogeneity: A comprehensive review. Water Resources Research. https://doi.org/10.1029/2008WR006993.
Hu, L. Y., & Jenni, S. (2005). History matching of object-based stochastic reservoir models. SPE Journal, 10(03), 312–323.
Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. IEEE Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/CVPR.2017.632.
Jin, Z. L., Liu, Y., & Durlofsky, L. J. (2019). Deep-learning-based reduced-order modeling for subsurface flow simulation. arXiv:1906.03729.
Jo, H., Santos, S., & Pyrcz, M. (2019). Conditioning stratigraphic, rule-based models with generative adversarial networks: a deepwater lobe example. In 2019 AAPG Annual Convention and Exhibition, San Antonio, Texas. https://doi.org/10.1306/42402Jo2019
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv:1412.6980.
Kolla, V., Posamentier, H. W., & Wood, L. J. (2007). Deep-water and fluvial sinuous channels—Characteristics, similarities and dissimilarities, and modes of formation. Marine and Petroleum Geology, 24(6–9), 388–405.
Laloy, E., Herault, R., Jacques, D., & Linde, N. (2018). Training-image based geostatistical inversion using a spatial generative adversarial neural network. Water Resources Research, 54(1), 381–406.
Laloy, E., Herault, R., Lee, J., Jacques, D., & Linde, N. (2017). Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network. Advances in Water Resources, 110, 387–405.
Laloy, E., Linde, N., Jacques, D., & Vrugt, J. A. (2015). Probabilistic inference of multi-Gaussian fields from indirect hydrological data using circulant embedding and dimensionality reduction. Water Resources Research, 51(6), 4224–4243.
LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
Li, X., Mariethoz, G., Lu, D. T., & Linde, N. (2016). Patch-based iterative conditional geostatistical simulation using graph cuts. Water Resources Research, 52(8), 6297–6320.
Mariethoz, G., & Caers, J. (2014). Multiple-point geostatistics: stochastic modeling with training models. Hoboken: Wiley.
Mariethoz, G., Renard, P., & Straubhaar, J. (2010). The direct sampling method to perform multiple-point geostatistical simulations. Water Resources Research. https://doi.org/10.1029/2008WR007621.
Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. arXiv:1411.1784.
Mo, S., Zhu, Y., Zabaras, N., Shi, X., & Wu, J. (2019). Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media. Water Resources Research, 55(1), 703–728.
Myerson, R. B. (1978). Refinements of the Nash equilibrium concept. International Journal of Game Theory, 7(2), 73–80.
Nguyen, A., Yosinski, J., & Clune, J. (2015). Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, (pp. 427–436).
Oliver, D. S., Reynolds, A. C., & Liu, N. (2008). Inverse theory for petroleum reservoir characterization and history matching. Cambridge: Cambridge University Press.
Onesti, L. J., & Miller, T. K. (1974). Patterns of variation in a fluvial system. Water Resources Research, 10(6), 1178–1186.
Øren, P. E., & Bakke, S. (2002). Process based reconstruction of sandstones and prediction of transport properties. Transport in Porous Media, 46(2–3), 311–343.
O’Shea, K., & Nash, R. (2015). An introduction to convolutional neural networks. arXiv:1511.08458.
Potdar, K., Pardawala, T. S., & Pai, C. D. (2017). A comparative study of categorical variable encoding techniques for neural network classifiers. International Journal of Computer Applications, 175(4), 7–9.
Pyrcz, M. J., Boisvert, J. B., & Deutsch, C. V. (2008). A library of training models for fluvial and deepwater reservoirs and associated code. Computers & Geosciences, 34(5), 542–560.
Pyrcz, M. J., Catuneanu, O., & Deutsch, C. V. (2005). Stochastic surface-based modeling of turbidite lobes. AAPG Bulletin, 89(2), 177–191.
Pyrcz, M. J., & Deutsch, C. V. (2005). Conditioning event-based fluvial models. Quantitative Geology and Geostatistics, 14, 135–144.
Pyrcz, M. J., & Deutsch, C. V. (2014). Geostatistical reservoir modeling. New York: Oxford University Press.
Pyrcz, M. J., McHargue, T., Clark, J., Sullivan, M., & Strebelle, S. (2012). Event-based geostatistical modeling: description and applications. Quantitative Geology and Geostatistics, 17, 27–38.
Pyrcz, M. J., Sech, R. I., Covault, J. A., Sun, T., Willis, B. R., & Sylvester, Z. (2014). Process-mimicking modeling considerations (pp. 1–16). Closing the Gap II: Advances in Applied Geomodelling for Hydrocarbon Reservoirs.
Pyrcz, M. J., Sech, R. P., Covault, J. A., Willis, B. J., Sylvester, Z., & Sun, T. (2015). Stratigraphic rule-based reservoir modeling. Bulletin of Canadian Petroleum Geology, 63(4), 287–303.
Ramanathan, R., Guin, A., Ritzi, R. W., Jr., Dominic, D. F., Freedman, V. L., Scheibe, T. D., et al. (2010). Simulating the heterogeneity in braided channel belt deposits: 1 A geometric-based methodology and code. Water Resources Research, 46, 4. https://doi.org/10.1029/2009WR008111.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: convolutional networks for biomedical image segmentation. In International Conference on Medical Image Computing and Computer-assisted Intervention, (pp. 234–241). https://doi.org/10.1007/978-3-319-24574-4_28.
Specht, D. F. (1991). A general regression neural network. IEEE Transactions on Neural Networks, 2(6), 568–576.
Strebelle, S. B., & Journel, A. G. (2001). Reservoir modeling using multiple-point statistics. In SPE Annual Technical Conference and Exhibition, 30 September–3 October, New Orleans, Louisiana. https://doi.org/10.2118/71324-MS.
Sun, T., Meakin, P., Jøssang, T., & Schwarz, K. (1996). A simulation model for meandering rivers. Water Resources Research, 32(9), 2937–2954.
Swanson, D. C. (1993). The importance of fluvial processes and related reservoir deposits. Journal of Petroleum Technology, 45(04), 368–377.
Thomas, R. G., Smith, D. G., Wood, J. M., Visser, J., Calverley-Range, E. A., & Koster, E. H. (1987). Inclined heterolithic stratification-terminology, description, interpretation and significance. Sedimentary Geology, 53(1–2), 123–179.
Wang, Y. C., Pyrcz, M. J., Catuneanu, O., & Boisvert, J. B. (2018). Conditioning 3D object-based models to dense well data. Computers & Geosciences, 115, 1–11. https://doi.org/10.1016/j.cageo.2018.02.006.
Warrick, A. W., & Myers, D. E. (1987). Optimization of sampling locations for variogram calculations. Water Resources Research, 23(3), 496–500. https://doi.org/10.1029/WR023i003p00496.
Williams, C. K. I. (1998). Prediction with Gaussian processes: from linear regression to linear prediction and beyond. Learning in Graphical Models, 89, 599–621.
Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? In Proceedings of the 27th International Conference on Neural Information Processing Systems, (vol. 2, pp. 3320–3328).
Zhang, Y., Person, M., Paola, C., Gable, C. W., Wen, X. H., & Davis, J. M. (2005). Geostatistical analysis of an experimental stratigraphy. Water Resources Research. https://doi.org/10.1029/2004WR003756.
Zhang, X., Pyrcz, M. J., & Deutsch, C. V. (2009). Stochastic surface modeling of deepwater depositional systems for improved reservoir models. Journal of Petroleum Science and Engineering, 68(1–2), 118–134.
Zhang, T. F., Tilke, P., Dupont, E., Zhu, L. C., Liang, L., & Bailey, W. (2019). Generating geologically realistic 3D reservoir facies models using deep learning of sedimentary architecture with generative adversarial networks. Petroleum Science, 16, 541–549.
Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the 2017 IEEE International Conference on Computer Vision, (pp. 2242–2251). https://doi.org/10.1109/ICCV.2017.244.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Pan, W., Torres-Verdín, C. & Pyrcz, M.J. Stochastic Pix2pix: A New Machine Learning Method for Geophysical and Well Conditioning of Rule-Based Channel Reservoir Models. Nat Resour Res 30, 1319–1345 (2021). https://doi.org/10.1007/s11053-020-09778-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11053-020-09778-1