1887
  1. Home
  2. Conferences
  3. Conference Proceedings
  4. ECMOR XVII
  5. Conference paper

Abstract

Summary

Seismic history matching can play a key role in geological characterization and uncertainty quantification. However, challenges related to intensive computational demands and complexity restricts its application in many practical cases. This paper presents a conceptual deep-learning-based framework fully deployed in the popular Pytorch architecture to accelerate the seismic history matching. We introduce a surrogate model based on a deep convolutional neural network with a stack of dense blocks, specifically a conditional deep convolutional autoencoder-decoder architecture (cDCAE). The surrogate model allows us to fully deploy data assimilation algorithms in Pytorch architecture and hence to easily make full use of the efficient computing units, in particular GPU’s for the matrix-matrix and matrix-vector multiplications. The feature of built-in automatic differentiation (AD) provided by Pytorch also makes is possible to evaluate gradient information efficiently in a parallel manner. Furthermore, it has been acknowledged to benefit from the deep learning practice of using stochastic gradient (SG) optimizers, e.g., Adam, instead of full gradient optimizers, e.g., Quasi-Newton, as is most common in conventional big-data assimilation. The proposed framework is tested on a benchmark 3D model in the context of petroleum engineering. This surrogate model is demonstrated to be capable of accurately predicting the quantity of interest, e.g., dynamic saturation maps for new geological realizations. Assessments demonstrating high surrogate-model accuracy are presented for an ensemble of test models. The robustness and dramatic speedup provided by the surrogate model suggests that it can help facilitate the application of large-scale seismic history matching.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202035158
2020-09-14
2024-04-26

  • From This Site

    /content/papers/10.3997/2214-4609.202035158
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. [1]Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I.J., Harp, A., Irving, G., Isard, M., Jia, Y., Józe-fowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Mané, D., Monga, R., Moore, S., Murray, D.G., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P.A., Vanhoucke, V., Vasudevan, V., Viégas, F.B., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y. and Zheng, X. [2016] TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. CoRR, abs/1603.04467.
     [Google Scholar]
  2. [2]Ahmadi, M.A. [2015] Developing a robust surrogate model of chemical flooding based on the artificial neural network for enhanced oil recovery implications. Mathematical Problems in Engineering, 2015.
     [Google Scholar]
  3. [3]Bishop, C.H., Frolov, S., Allen, D.R., Kuhl, D.D. and Hoppel, K. [2017] The Local Ensemble Tangent Linear Model: an enabler for coupled model 4D-Var. Quarterly Journal of the Royal Meteorological Society, 143(703), 1009–1020.
     [Google Scholar]
  4. [4]Courant, R. and Hilbert, D. [1962] Methods of mathematical physics: Wiley Interscience.
     [Google Scholar]
  5. [5]Courtier, P., Thépaut, J.N. and Hollingsworth, A. [1994] A strategy for operational implementation of 4D-Var, using an incremental approach. Quarterly Journal of the Royal Meteorological Society, 120(519), 1367–1387.
     [Google Scholar]
  6. [6]Dai, C., Xue, L., Zhang, D. and Guadagnini, A. [2016] Data-worth analysis through probabilistic collocation-based Ensemble Kalman Filter. Journal of Hydrology, 540, 488–503.
     [Google Scholar]
  7. [7]Frolov, S. and Bishop, C.H. [2016] Localized ensemble-based tangent linear models and their use in propagating hybrid error covariance models. Monthly Weather Review, 144(4), 1383–1405.
     [Google Scholar]
  8. [8]G, E. [2009] Data assimilation: the ensemble Kalman filter. Springer Science & Business Media.
     [Google Scholar]
  9. [9]Gassmann, F. [1951] Elastic waves through a packing of spheres. Geophysics, 16(4), 673–685.
     [Google Scholar]
  10. [10]He, X., G.J. and Deng, L. [2014] Deep Learning for Natural Language Processing: Theory and Practice (Tutorial). Cikm.
     [Google Scholar]
  11. [11]He, K., Z.X.R.S., and Sun, J. [2016] Identity Mappings in Deep Residual Networks. In: European Conference on Computer Vision.
     [Google Scholar]
  12. [12]Heo, Y.J., K.S.K.D.L.K. and Chung, W. [2018] Super-High-Purity Seed Sorter Using Low-Latency Image-Recognition Based on Deep Learning. IEEE Robotics & Automation Letters, 3(4), 1–1.
     [Google Scholar]
  13. [13]Huang, G., L.Z.V.D.M.L. and Weinberger, K. [2016] Densely Connected Convolutional Networks.
     [Google Scholar]
  14. [14]Jin, Z.L., L.Y. and Durlofsky, L. [2019] Deep-learning-based reduced-order modeling for subsurface flow simulation. arXiv preprint arXiv:1906.03729.
     [Google Scholar]
  15. [15]Kani, J.N. and Elsheikh, A.H. [2018] Reduced order modeling of subsurface multiphase flow models using deep residual recurrent neural networks. Transport in Porous Media.
     [Google Scholar]
  16. [16]Liu, C., X.Q. and Wang, B. [2008] An ensemble-based four-dimensional variational data assimilation scheme. Part I: Technical formulation and preliminary test. Monthly Weather Review, 136(9), 3363–3373.
     [Google Scholar]
  17. [17]Liu, C., X.Q. and Wang, B. [2009] An ensemble-based four-dimensional variational data assimilation scheme. Part II: Observing system simulation experiments with Advanced Research WRF (ARW). Monthly Weather Review, 137(5), 1687–1704.
     [Google Scholar]
  18. [18]Matthews, J.D., C.J.S.K.Z.R.S.A.M.T. and Howell, J. [2008] Assessing the effect of geological uncertainty on recovery estimates in shallow-marine reservoirs: the application of reservoir engineering to the SAIGUP project. Petroleum Geoscience, 14(1), 35–44.
     [Google Scholar]
  19. [19]Mo, S., Z.N.S.X. and Wu, J. [2018] Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification.
     [Google Scholar]
  20. [20]Mo, S., Z.Y.Z.N.S.X. and Wu, J. [2019] Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multiphase flow in heterogeneous media. Water Resources Research, 55(1).
     [Google Scholar]
  21. [21]Paszke, A., G.S.M.F.L.A.B.J.C.G.K.T.L.Z.G.N.A.L. and Desmaison, A. [2019] PyTorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems. 8024–8035.
     [Google Scholar]
  22. [22]Rasmussen, A.F., S.T.B.K.L.A.H.J.S.B.K.R.B.M.R.A.S.O. and Lie, K. [2019] The Open Porous Media Flow Reservoir Simulator. arXiv preprint arXiv:1910.06059.
     [Google Scholar]
  23. [23]Ronneberger, O., F.P. and Brox, T. [2015] U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, 234–241.
     [Google Scholar]
  24. [24]Roy, P.T., El Moçayd, N., Ricci, S., Jouhaud, J.C., Goutal, N., De Lozzo, M. and Rochoux, M.C. [2018] Comparison of polynomial chaos and Gaussian process surrogates for uncertainty quantification and correlation estimation of spatially distributed open-channel steady flows. Stochastic environmental research and risk assessment, 32(6), 1723–1741.
     [Google Scholar]
  25. [25]Savchenko, A. [2017] Probabilistic Neural Network with Complex Exponential Activation Functions in Image Recognition using Deep Learning Framework. PP(99).
     [Google Scholar]
  26. [26]Tang, M., L.Y. and Durlofsky, L. [2019] A deep-learning-based surrogate model for data assimilation in dynamic subsurface flow problems. arXiv preprint arXiv:1908.05823.
     [Google Scholar]
  27. [27]Tripathy, R. and Bilionis, I. [2018] Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification. Journal of Computational Physics, 375, S0021999118305655–.
     [Google Scholar]
  28. [28]Young, T., H.D.P.S. and Cambria, E. [2018] Recent Trends in Deep Learning Based Natural Language Processing [Review Article]. IEEE Computational Intelligence Magazine, 13(3), 55–75.
     [Google Scholar]
  29. [29]Zhang, Y., T.Y.K.Y.Z.B. and Fu, Y. [2018] Residual Dense Network for Image Super-Resolution.
     [Google Scholar]
  30. [30]Zhong, Z., S.A. and Jeong, H. [2019] Predicting CO2 Plume Migration in Heterogeneous Formations Using Conditional Deep Convolutional Generative Adversarial Network. Water Resources Research.
     [Google Scholar]
  31. [31]Zhu, Y. and Zabaras, N. [2018] Bayesian Deep Convolutional encoder-decoder Networks for Surrogate Modeling and Uncertainty Quantification. Journal of Computational Physics, 366.
     [Google Scholar]
  32. [32]Zhu, Y., Z.N.K.P. and Perdikaris, P. [2019] Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data.
     [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202035158
Loading
Deep-Learning Inversion to Efficiently Handle Big-Data Assimilation: Application to Seismic History Matching
Conference Proceedings 2020, 1 (2020); https://doi.org/10.3997/2214-4609.202035158
/content/papers/10.3997/2214-4609.202035158
/content/papers/10.3997/2214-4609.202035158
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error