SpringerLink
Log in

Using a machine learning proxy for localization in ensemble data assimilation

  • Original Paper
  • Published:
Computational Geosciences Aims and scope Submit manuscript

Abstract

Ensemble data assimilation methods, particularly iterative forms of ensemble smoother, are very useful assisted history matching techniques. One of the main challenges in the application of these methods is the excessive variance loss due to sampling errors occasioned by the limited size ensembles used in practical cases. The standard procedure to mitigate this problem is called distance-based localization. However, in this case, the data assimilation performance becomes highly dependent on the choice of the localization region. Moreover, there are several relevant examples of non-local model parameters and data types, in which cases, distance-based localization does not apply. This paper proposes a distance-free localization procedure that combines a least-squares support vector (LS-SVR) proxy with a non-isotropic tapering function proposed in the literature. We tested the proposed method in two versions of the PUNQ-S3 problem. In the first version, we tested the method to localize scalar (non-local) parameters. The results show relevant improvements, especially in terms of preserving the posterior variance of the ensemble compared to methods investigated in Lacerda et al. (J. Pet. Sci. Eng. 172,690–706, 2019). The second version considered the problem of localization of grid parameters. In this case, the proposed method outperformed a distance-based localization approach proposed in the literature.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Aanonsen, S.I., Nævdal, G., Oliver, D.S., Reynolds, A.C., Vallè, s, B.: Review of ensemble Kalman filter in petroleum engineering. SPE J. 14(3), 393–412 (2009). https://doi.org/10.2118/117274-PA

    Article  Google Scholar 

  2. Abadpour, A., Adejare, M., Chugunova, T., Mathieu, H., Haller, N.: Integrated geo-modeling and ensemble history matching of complex fractured carbonate and deep offshore turbidite fields, generation of several geologically coherent solutions using ensemble methods. In: Proceedings of the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 12–15 November, number SPE-193028-MS (2018), https://doi.org/10.2118/193028-MS

  3. Arroyo-Negrete, E., Devegowda, D., Datta-Gupta, A., Choe, J.: Streamline-assisted ensemble Kalman filter for rapid and continuous reservoir model updating. SPE Reserv. Evaluation Eng. 11(6), 1046–1060 (2008). https://doi.org/10.2118/104255-PA

    Article  Google Scholar 

  4. Bannister, R.N.: How is the balance of a forecast ensemble affected by adaptive and nonadaptive localization schemes?. Mon. Weather. Rev. 143, 3680–3699 (2015). https://doi.org/10.1175/MWR-D-14-00379.1

    Article  Google Scholar 

  5. Bishop, C.H., Hodyss, D.: Flow-adaptive moderation of spurious ensemble correlations and its use in ensemble-based data assimilation. Q. J. Roy. Meteorol. Soc. 133(629), 2029–2044 (2007). https://doi.org/10.1002/qj.169

    Article  Google Scholar 

  6. Boser, B.E., Guyon, I.M., Vapnik, V.N.: A training algorithm for optimal margin classifiers. In: COLT ’92 Proceedings of the fifth Annual Workshop on Computational Learning Theory Pittsburgh, Pennsylvania, USA, July 27–29, pp 144–152 (1992), https://doi.org/10.1145/130385.130401

  7. Bruyelle, J., Guérillot, D.: Neural networks and their derivatives for history matching and reservoir optimization problems. Comput. Geosci. 18(3–4), 549–561 (2014). https://doi.org/10.1007/s10596-013-9390-y

    Article  Google Scholar 

  8. Chen, Y., Oliver, D.S.: Cross-covariance and localization for enKF in multiphase flow data assimilation. Comput. Geosci. 14(4), 579–601 (2010). https://doi.org/10.1007/s10596-009-9174-6

    Article  Google Scholar 

  9. Chen, Y., Oliver, D.S.: History matching of the Norne full-field model with an iterative ensemble smoother. SPE Reserv. Evaluation Eng. 17(2). DOI10.2118/164902-PA (2014)

  10. Devegowda, D., Arroyo-Negrete, E., Datta-Gupta, A., Douma, S.G.: Efficient and robust reservoir model updating using ensemble Kalman filter with sensitivity-based covariance localization. In: Proceedings of the SPE Reservoir Simulation Symposium, Houston, Texas, USA 26–28 February number SPE-106144-MS (2007), https://doi.org/10.2118/106144-MS

  11. Emerick, A.A.: Analysis of the performance of ensemble-based assimilation of production and seismic data. J. Pet. Sci. Eng. 139, 219–239 (2016). https://doi.org/10.1016/j.petrol.2016.01.029

    Article  Google Scholar 

  12. Emerick, A.A., Reynolds, A.C.: History matching a field case using the ensemble Kalman filter with covariance localization. SPE Reserv. Evaluation Eng. 14(4), 423–432 (2011a). 10.2118/141216-PA

    Article  Google Scholar 

  13. Emerick, A.A., Reynolds, A.C.: Combining sensitivities and prior information for covariance localization in the ensemble Kalman filter for petroleum reservoir applications. Comput. Geosci. 15(2), 251–269 (2011b). https://doi.org/10.1007/s10596-010-9198-y

    Article  Google Scholar 

  14. Emerick, A.A., Reynolds, A.C.: Investigation on the sampling performance of ensemble-based methods with a simple reservoir model. Comput. Geosci. 17(2), 325–350 (2013a). https://doi.org/10.1007/s10596-012-9333-z

    Article  Google Scholar 

  15. Emerick, A.A., Reynolds, A.C.: Ensemble smoother with multiple data assimilation. Comput. Geosci 55, 3–15 (2013b). https://doi.org/10.1016/j.cageo.2012.03.011

    Article  Google Scholar 

  16. Evensen, G., Eikrem, K.S.: Conditioning reservoir models on rate data using ensemble smoothers. Computational Geosciences First Online https://doi.org/10.1007/s10596-018-9750-8 (2018)

  17. 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(SUPP), 87–96 (2001). https://doi.org/10.1144/petgeo.7.S.S87

    Article  Google Scholar 

  18. Furrer, R., Bengtsson, T.: Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter variants. J. Multivar. Anal. 98(2), 227–255 (2007). https://doi.org/10.1016/j.jmva.2006.08.003

    Article  Google Scholar 

  19. Gao, G., Vink, J.C., Chen, C., Khamra, Y.E., Tarrahi, M.: Distributed Gauss-Newton optimization method for history matching problems with multiple best matches. Comput. Geosci. 21, 1325–1342 (2017). https://doi.org/10.1007/s10596-017-9657-9

    Article  Google Scholar 

  20. Gaspari, G., Cohn, S.E.: Construction of correlation functions in two and three dimensions. Q. J. Roy. Meteorol. Soc. 125(554), 723–757 (1999). https://doi.org/10.1002/qj.49712555417

    Article  Google Scholar 

  21. Guo, Z., Reynolds, A.C.: Robust life-cycle production optimization with a support-vector-regression proxy. SPE J. 23(6), 2409–2427 (2018). https://doi.org/10.2118/191378-PA

    Article  Google Scholar 

  22. Guo, Z., Chen, C., Gao, G., Cao, R., Li, R., Liu, C.: EUR assessment of unconventional assets using machine learning and distributed computing techniques. In: Proceedings of the SPE/AAPG/SEG Unconventional Resources Technology Conference, Austin, Texas, USA, 24–26 July, number URTEC-2659996-MS (2017a), https://doi.org/10.15530/URTEC-2017-2659996

  23. Guo, Z., Chen, C., Gao, G., Vink, J.: Applying support vector regression to reduce the effect of numerical noise and enhance the performance of history matching. In: Proceedings of the SPE Annual Technical Conference and Exhibition, San Antonio, Texas, USA, 9–11 October, number SPE-187430-MS (2017b), https://doi.org/10.2118/187430-MS

  24. Houtekamer, P.L., Mitchell, H.L.: A sequential ensemble Kalman filter for atmospheric data assimilation. Mon. Weather Rev. 129(1), 123–137 (2001). https://doi.org/10.1175/1520-0493(2001)129<0123:ASEKFF>2.0.CO;2

    Article  Google Scholar 

  25. Lacerda, J.M., Emerick, A.A., Pires, A.P.: Methods to mitigate loss of variance due to sampling errors in ensemble data assimilation with non-local model parameters. J. Pet. Sci. Eng. 172, 690–706 (2019). https://doi.org/10.1016/j.petrol.2018.08.056

    Article  Google Scholar 

  26. Luo, X., Bhakta, T., Nævdal, G.: Correlation-based adaptive localization with applications to ensemble-based 4D-seismic history matching. SPE J. 23(2), 396–427 (2018a). https://doi.org/10.2118/185936-PA

    Article  Google Scholar 

  27. Luo, X., Lorentzen, R.J., Valestrand, R., Evensen, G.: Correlation-based adaptive localization for ensemble-based history matching: Applied to the Norne field case study. SPE Reservoir Engineering, Preprint, https://doi.org/10.2118/191305-PA (2018b)

  28. Maucec, M., Ravanelli, F.M.D.M., Lyngra, S., Zhang, S.J., Alramadhan, A.A., Abdelhamid, O.A., Al-Garni, S.A.: Ensemble-based assisted history matching with rigorous uncertainty quantification applied to a naturally fractured carbonate reservoir. In: Proceedings of the SPE Annual Technical Conference and Exhibition, Dubai, UAE, 26–28 September, number SPE-181325-MS (2016), https://doi.org/10.2118/181325-MS

  29. Oliver, D.S., Reynolds, A.C., Liu, N.: Inverse Theory for Petroleum Reservoir Characterization and History Matching. Cambridge University Press, Cambridge (2008)

    Book  Google Scholar 

  30. Perrone, A., Pennadoro, F., Tiani, A., Rossa, E.D., Sætrom, J.: Enhancing the geological models consistency in ensemble based history matching an integrated approach. In: Proceedings of the SPE Reservoir Characterisation and Simulation Conference and Exhibition, Abu Dhabi UAE, 8–10 May number SPE-186049-MS (2017), https://doi.org/10.2118/186049-MS

  31. Quadrianto, N., Kersting, K., Xu, Z.: Gaussian Process. Springer, US (2011)

    Google Scholar 

  32. Rana, S., Ertekin, T., King, G.R.: An efficient assisted history matching and uncertainty quantification workflow using gaussian processes proxy models and variogram based sensitivity analysis: GP-VARS. Comput. Geosci. 114, 73–83 (2018). https://doi.org/10.1016/j.cageo.2018.01.019

    Article  Google Scholar 

  33. Sætrom, J., Morell, E., Ravari, R.R., Maitre, C.L., Seldal, M. : Fast integrated reservoir modelling on the Gjøa field offshore Norway. In: Proceedings of the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, 13–16 November number SPE-188557-MS (2017), https://doi.org/10.2118/188557-MS

  34. Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14(3), 199–222 (2004). https://doi.org/10.1023/B:STCO.0000035301.49549.88

    Article  Google Scholar 

  35. Sousa, E.P.S., Reynolds, A.C.: Markov chain Monte Carlo uncertainty quantification with a least-squares support vector regression proxy. In: Proceedings of the SPE Reservoir Simulation Conference, Galveston, Texas, USA, 10–11 April, number SPE-193918-MS (2019), https://doi.org/10.2118/193918-MS

  36. Suykens, J.A.K., Vandewalle, J.: Least squares support vector machine classifiers. Neural Process. Lett. 9(3), 293–300 (1999). https://doi.org/10.1023/A:1018628609742

    Article  Google Scholar 

  37. Thulin, K., Nævdal, G., Skaug, H.J., Aanonsen, S.I.: Quantifying Monte Carlo uncertainty in the ensemble Kalman field. SPE J. 16(1), 172–182 (2011). https://doi.org/10.2118/123611-PA

    Article  Google Scholar 

  38. Zhang, Y., Oliver, D.S.: Improving the ensemble estimate of the Kalman gain by bootstrap sampling. Math. Geosci. 42, 327–345 (2010). https://doi.org/10.1007/s11004-010-9267-8

    Article  Google Scholar 

  39. Zubarev, D.I.: Pros and cons of applying proxy-models as a substitute for full reservoir simulations. In: Proceedings of the SPE Annual Technical Conference and Exhibition, New Orleans, Louisiana, 4–7 October, number SPE-124815-MS (2009), https://doi.org/10.2118/124815-MS

Download references

Acknowledgements

The authors thank Petrobras for supporting this research and for the permission to publish this paper. This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Finance Code 001.

Author information

Authors and Affiliations

  1. Petrobras, Av. Elias Agostinho 665, Imbetiba, Macaé, RJ, 27913-350, Brazil

    Johann M. Lacerda

  2. Petrobras, Rio de Janeiro, Brazil

    Alexandre A. Emerick

  3. Universidade Estadual do Norte Fluminense Darcy Ribeiro, Macaé/RJ, Brazil

    Adolfo P. Pires

Authors
  1. Johann M. Lacerda
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alexandre A. Emerick
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adolfo P. Pires
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Johann M. Lacerda.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lacerda, J.M., Emerick, A.A. & Pires, A.P. Using a machine learning proxy for localization in ensemble data assimilation. Comput Geosci 25, 931–944 (2021). https://doi.org/10.1007/s10596-020-10031-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10596-020-10031-0

Keywords

Search

Navigation