1887

Abstract

Summary

The estimation and uncertainty quantification of channelized reservoirs in a data assimilation framework is very hard to achieve due to the geometrical and topological characteristics of the facies fields. The channelized structure is broken after the updated step of the data assimilation process, and this causes unrealistic updated reservoir models. Geological realism can be achieved in two ways, either by learning or by conditional sampling from the prior distribution. In this study, we train a convolutional autoencoder (CAE) to reconstruct the channelized structure of a reservoir with three facies types namely channel, levee, and shale, where there is a topological transition between them. The training is done with a set composed of pairs of images, of which one is perturbed, and the other has a correct geometrical and topological structure. The CAE is linked with a parameterization of the facies fields and became part of it. The enhanced parameterization is further coupled with ES-MDA for history matching. The results show that the updated facies fields keep the prior channelized structure, and the indicators of a good history matching are fulfilled. This means good results in terms of facies estimation, uncertainty quantification, data match, and prediction capabilities of the updated ensemble.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202335023
2023-11-27
2026-01-16

  • From This Site

    /content/papers/10.3997/2214-4609.202335023
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Canchumuni, S., Emerick, A. and Pacheco, M., [2019b] Towards a robust parameterization for conditioning faciesmodels using deep variational autoencoders and ensemble smoother. Computers & Geosciences128:87–102.ISSN: 0098–3004. https://doi.org/10.1016/j.cageo.2019.04.006.
     [Google Scholar]
  2. Canchumuni, S., Castro, J., Potratz, J., Emerick, A. and Pacheco, M. [2021], Recent developments combining ensemble smoother and deep generative networks for facies history matching. Comput Geosci25:433–466. https://doi.org/10.1007/s10596-020-10015-0
     [Google Scholar]
  3. Emerick, A.A. and Reynolds, A.C. [2013] Ensemble smoother with multiple data assimilation. Computers &Geosciences55:3–15. https://doi.org/10.1016/j.cageo.2012.03.011.
     [Google Scholar]
  4. Sebacher, B., Stordal, A.S. and Hanea, R., [2015] Bridging multi-point statistics and truncated Gaussian fields for improved estimation of channelized reservoirs with ensemble methods. Computational Geosciences19(2):341–369. https://doi.org/10.1007/s10596-014-9466-3.
     [Google Scholar]
  5. Sebacher, B., Stordal, A. and Hanea, R. [2016] Complex geology estimation using the iterative adaptive Gaussian mixture filter. Computational Geosciences20(1):133–148. https://doi.org/10.1007/s10596-015-9553-0
     [Google Scholar]
  6. Sebacher, B. and Hanea, R. [2020] Channelized reservoir estimation using a low-dimensional parameterization based on high-order singular value decomposition. Computational Geosciences24:509–531. https://doi.org/10.1007/s10596-019-09856-1
     [Google Scholar]
  7. Sebacher, B. and Toma, S-A. [2022] Bridging Deep Convolutional Autoencoders and Ensemble Smoothers for Improved Estimation of Channelized Reservoirs.Mathematical Geosciences54:903–939. https://doi.org/10.1007/s11004-022-09997-7.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202335023
Loading
History Matching of Three Facies Channelized Reservoirs Using Ensemble Smoothers with a Convolutional Autoencoder Based Parameterization
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202335023
/content/papers/10.3997/2214-4609.202335023
/content/papers/10.3997/2214-4609.202335023
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