1887

Abstract

Summary

We present an approach to generate reservoir models conditioned on well log and production data along with uncertainty estimation with Variational Autoencoders based on Graph Convolutions. This approach demonstrates the ability to implicitly parameterize geological representations into a latent space of reduced dimensionality and provides ways to uncertainty quantification and production profiling across multiple geological concepts. GVAE links the static model and its dynamic response via latent space, which is a reduced-order representation of geological model complexity. GVAE can handle unstructured data represented as graphs, opposed to a conventional VAE applied in similar works. On the Brugge field dataset, we showed that GVAE reliably reproduces geology by comparison static and dynamic properties of reference (initial) model with generated representations. GVAE utilizes the notion of a latent space depicting the variation of geological concepts and other geological properties. Navigation and optimization through the latent space provide a model update and an ensemble of history-matched models.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202335051
2023-11-27
2026-01-18

  • From This Site

    /content/papers/10.3997/2214-4609.202335051
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Bronstein, M.M., Bruna, J., LeCun, Y., Szlam, A., Vandergheynst, P., 2016. Geometric deep learning: going beyond Euclidean data.IEEE Signal Processing Magazine34, 18–42.
     [Google Scholar]
  2. Canchumuni, S.A., Emerick, A.A., Pacheco, M.A., 2017. Integration of Ensemble Data Assimilation and Deep Learning for History Matching Facies Models, in: Day 1 Tue October 24, 2017.
     [Google Scholar]
  3. Chan, S., Elsheikh, A.H., 2019. Parametric generation of conditional geological realizations using generative neural networks.Computational Geosciences23, 925–952.
     [Google Scholar]
  4. Doersch, C., 2016. Tutorial on Variational Autoencoders.
     [Google Scholar]
  5. Morris, C., Ritzert, M., Fey, M., Hamilton, W.L., Lenssen, J.E., Rattan, G., Grohe, M., 2020. Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks.
     [Google Scholar]
  6. Mosser, L., Dubrule, O., Blunt, M.J., 2019. DeepFlow: History Matching in the Space of Deep Generative Models.
     [Google Scholar]
  7. Peters, E.., Arts, R.J.. J., Brouwer, G.K.. K., Geel, C.R.. R., Cullick, S.., Lorentzen, R.J.. J., Chen, Y.., Dunlop, K.N.B.. N.B., Vossepoel, F.C.. C., Xu, R.., Sarma, P.., Alhutali, A.H.. H., and A.C.. C.Reynolds. “Results of the Brugge Benchmark Study for Flooding Optimization and History Matching.” SPE Res Eval & Eng13 (2010): 391–405.
     [Google Scholar]
  8. Nikolaus Hansen Inria, 2016The CMA Evolution Strategy: A Tutorial
     [Google Scholar]
  9. Shishaev, G., Demyanov, V., Arnold, D. and Vygon, R.History Matching and Uncertainty Quantification of Reservoir Performance with Generative Deep Learning and Graph Convolutions.European Association of Geoscientists & Engineers. ECMOR2022, Sep 2022, Volume 2022, p.1 – 9
     [Google Scholar]
/content/papers/10.3997/2214-4609.202335051
Loading
Application of Graph Variational Autoencoders for History Matching Problem of Brugge Field
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202335051
/content/papers/10.3997/2214-4609.202335051
/content/papers/10.3997/2214-4609.202335051
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