1887

Abstract

Summary

The proposed new nonlinear technique based on full functional Kolmogorov neural network for the well log prediction using several seismic cubes and low-frequency model allows for getting high-resolution results. Application of Kolmogorov full functional neural network makes it possible to achieve a high level of freedom deep learning operator with only one hidden layer. The learning procedure is based on hybrid technique using Kolmogorov’s superposition theorem and genetic approach with A. N. Tikhonov regularization.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202053084
2020-11-16
2024-04-25
Loading full text...

Full text loading...

References

  1. Kobrunov, A. and Priezzhev, I.
    [2016] Hybrid combination genetic algorithm and controlled gradient method to train a neural network, Geophysics, 81, no. 4, 1–9.
    [Google Scholar]
  2. KolmogorovA. N.
    , [1957] On the representation of continuous functions of several variables as superpositions of continuous functions of one variable and addition, Dokl. USSR Academy of Sciences, 1957, vol.114, number 5953–956.
    [Google Scholar]
  3. Priezzhev, I., Shmaryan, L. and Bejarano, G.
    [2008] Non-linear multi trace seismic inversion using neural network and genetic algorithm - "Genetic Inversion": Annual Meeting St Petersburg, EAGE, Extended Abstracts
    [Google Scholar]
  4. Tikhonov, A. N. and ArseninV. Y.
    [1977] Solutions of ill-posed problems, V H Winston and Sons, Washington D.C.
    [Google Scholar]
  5. Veeken, P.C.H., Priezzhev, Shmaryan, L.E., Shteyn, Y.I., Barkov, A.Y. and Ampilov, Y.P.
    [2009] Non-linear multi-trace genetic inversion applied on seismic data across the Shtokman field (offshore northern Russia): Geophysics, 74, no. 6, 49–59.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202053084
Loading
/content/papers/10.3997/2214-4609.202053084
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