1887

Abstract

Summary

We have developed a novel inverse methodology workflow using Nvidia Modulus’s physics-informed neural operator (PINO) as a fast surrogate to solve the black-oil forward problem together with a modified Bayesian adaptive ensemble Kalman inversion (aREKI) approach parametrized with deep neural network (DNN) exotic priors. The DNN prior used here are the variational convolution autoencoder and a novel mixture of deep neural network experts, and together with the developed aREKI method is optimal for sampling non-Gaussian posterior measures, like situations found in channelized reservoirs. The output from the PINO model is the pressure and water saturation fields, and the inputs are the absolute permeability, effective porosity,time-step,initial pressure & saturation, and source and sink terms. The overall workflow is successful in recovering the unknown channelized absolute permeability & effective porosity field for this synthetic case, using an ensemble of 5,000 members with about 100X speedup to traditional numerical approaches. The workflow is suitable for forward and inverse reservoir uncertainty quantification tasks for rapid reservoir management operational decision strategies.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.2023630004
2023-09-25
2025-11-09

  • From This Site

    /content/papers/10.3997/2214-4609.2023630004
    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.S.Rojas, J.Koplik, Nonlinear flow in porous media, Phys. Rev. E58 (1998) 4776–4782. doi:10.1103/PhysRevE.58.4776.URL, https://link.aps.org/doi/10.1103/PhysRevE.58.4776
     https://doi.org/10.1103/PhysRevE.58.4776.URL [Google Scholar]
  2. 2.Nocedal, J. and Wright, S. J., 1999.Numerical Optimization, Springer, New York
     [Google Scholar]
  3. 3.StuartA M, 2010Inverse problems: A Bayesian perspective Acta Numerica19451–559.
     [Google Scholar]
  4. 4.Hansen, T.M., Vu, L.T., and Bach, T.2016. MPSLIB: A C++ class for sequential simulation of multiple-point statistical models, in SoftwareX, doi:10.1016/j.softx.2016.07.001.[pdf,www].
     https://doi.org/10.1016/j.softx.2016.07.001 [Google Scholar]
  5. 5.David E.Bernholdt, Mark R.Cianciosa, David L.Green, Jin M.Park, Kody J. H.Law, and ClementEtienam. Cluster, classify, regress: A general method for learning discontinuous functions.Foundations of Data Science, 1(2639-8001-2019-4-491):491, 2019.
     [Google Scholar]
  6. 6.DornO & VillegasR, 2008History matching of petroleum reservoirs using a level set technique, Inverse problems Volume: 24 Issue: 3 Article Number: 035015
     [Google Scholar]
  7. 7.Oliver, D. S. & Chen, Y., 2010. Recent progress on reservoir history matching: a review. s.l.: Computational Geoscience - Springer Science
     [Google Scholar]
  8. 8.Evensen, G., 2003. The Ensemble Kalman Filter: Theoretical formulation and practical implementation.Ocean Dynamics, 53(4), pp. 343–367
     [Google Scholar]
  9. 9.I.Goodfellow, Y.Bengio, A.Courville, 2016. Deep Learning, MIT Press. URL http://www.deeplearningbook.org
     [Google Scholar]
  10. 10.Nvidia Modulus, a framework for surrogate simulations: https://developer.nvidia.com/modulus
     [Google Scholar]
  11. 11.ZongyiLi, NikolaKovachki, KamyarAzizzadenesheli, BurigedeLiu, KaushikBhattacharya, AndrewStuart, AnimaAnandkumar. Fourier Neural Operator for Parametric Partial Differential Equations.https://doi.org/10.48550/arXiv.2010.08895
     [Google Scholar]
  12. 12.Naumov, Maxim, et al. “AmgX: A library for GPU accelerated algebraic multigrid and preconditioned iterative methods.” SIAM Journal on Scientific Computing37.5 (2015): S602–S626
     [Google Scholar]
/content/papers/10.3997/2214-4609.2023630004
Loading
A Reservoir Model Characterization with a Bayesian Framework and a Modulus based Physics constrained Neural Operator
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.2023630004
/content/papers/10.3997/2214-4609.2023630004
/content/papers/10.3997/2214-4609.2023630004
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