1887
  1. Home
  2. Conferences
  3. Conference Proceedings
  4. Saint Petersburg 2020
  5. Conference paper

Abstract

Summary

In this study, we propose a new approach to borehole resistivity images interpretation, based on combination of 3D finite element simulation and convolutional neural network (CNN) algorithms. The CNN is trained on the results of 3D numerical simulation to detect geoelectric boundaries. High-performance parallel computing and data augmentation are used in order to minimize the time needed to obtain a set of images sufficient for CNN training. Despite the time-consuming processes of synthetic data obtaining and CNN training, the algorithm application does not require serious computing resources and takes seconds. The advantage of the developed algorithm is the ability to process images of an arbitrary length, due to the absence of fully connected layers in the CNN architecture.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202053015
2020-11-16
2023-03-22

  • From This Site

    /content/papers/10.3997/2214-4609.202053015
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Danilovskiy, K.N., Dudaev, A.R., Glinskikh, V.N., Nikitenko, M.N., Moskaev, I.A.
    [2019] Web-technologies based software for oil and gas wells geosteering. Vestník NSU. Series: Information Technologies, 17(2), 5–17.
     [Google Scholar]
  2. Danilovskiy, K.N., Glinskikh, V.N., Nechaev, O.V.
    [2018] 3D modelling of the new resistivity microimaging tool signals for logging while drilling. 80th EAGE Conference & Exhibition 2018, Extended Abstracts, Tu SP2 01.
     [Google Scholar]
  3. Glinskikh, V.N., Danilovskiy, K.N. and Nechaev, O.V.
    [2018] 3D numerical simulation of the azimuthal micro-lateral logging signals during drilling. Geology, geophysics and development of oil and gas fields, 10, 32–39.
     [Google Scholar]
  4. Gupta, K.D., Vallega, V., Maniar, H., Marza, P., Xie, H., Ito, K. and Abubakar, A.
    [2019] A deep-learning approach for borehole image interpretation. SPWLA 60th Annual Logging Symposium, Transactions, T60ALS-2019_BB.
     [Google Scholar]
  5. Kherroubi, J., Meinhardt-Llopis, E., Grompone, R., Costes, J., Facciolo, G. and Morel, J.M.
    [2017] Automatic dip picking in borehole images. US patent, US 2017/0372490 A1.
     [Google Scholar]
  6. LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P.
    [1998] Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278–2324.
     [Google Scholar]
  7. Thapa, B.B., Hughett, P. and Karasaki, K.
    [1997] Semi-automatic analysis of rock fracture orientations from borehole wall images. Geophysics, 62(1), 129–137.
     [Google Scholar]
  8. Yamada, T., Kherroubi, J., He, A. and Matsumura, Y.
    [2018] Cloud-based borehole image interpretation workflow using machine learning. 80th EAGE Conference & Exhibition 2018, Extended Abstracts, Tu H 10.
     [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202053015
Loading
Automatic Geoelectric Boundaries Detection on the Resistivity Images Based on 3D Numerical Simulation and Convolutional Neural Network
Conference Proceedings 2020, 1 (2020); https://doi.org/10.3997/2214-4609.202053015
/content/papers/10.3997/2214-4609.202053015
/content/papers/10.3997/2214-4609.202053015
Loading

Data & Media loading...

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