1887
PDF

Abstract

Summary

In presentation shows example density cube prediction in carbonates in Caspian sea area to detect dolomitization zones using deep neural network. The prediction is based on full stack seismic cube and several well logs. To train deep neural networks we used hybrid training technique based on a combination: deep neural network input generalization for first layers, genetic algorithms together with a gradient methods and Tikhonov regularization. Using deep neural network allow to build prediction operator with high level of the power of freedom and as result good quality of the prediction.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.201702215
2017-09-11
2024-03-29
Loading full text...

Full text loading...

/deliver/fulltext/2214-4609/2017/43789.html?itemId=/content/papers/10.3997/2214-4609.201702215&mimeType=html&fmt=ahah

References

  1. Hampson, B., J.Schuelke, and J.Quirein
    , 2001, Use of multi-attribute transforms to predict log properties from seismic data: Geophysics, 66, no. 1, 3–46.
    [Google Scholar]
  2. KobrunovA., I.Priezzhev
    , 2016, Hybrid combination genetic algorithm and controlled gradient method to train a neural network, Geophysics, 81, no 4, 1–9.
    [Google Scholar]
  3. Kovalenko, K.V., Nooraiepour, M. and Masoud, A.
    , 2014, August. Predicting Effective Porosity by Genetic Inversion of Seismic Data in Zechstein Carbonates, North Sea. In 3rd EAGE International GeoBaikal conference 2014-Exploration and Field Development in East Siberia.
    [Google Scholar]
  4. Leginowicz, A. and Pirowska, K.,
    2013. Estymacja parametrów charakteryzujacych osrodek geologiczny przy pomocy procedury inwersji genetycznej (The estimation of rock properties characterizing reservoir using procedure of genetic inversion). Nafta-Gaz, 69.
    [Google Scholar]
  5. Leginowicz, A. and Pieniazek, K.,
    2012. Estymacja parametrów charakteryzujacych osrodek geologiczny za pomoca procedury inwersji genetycznej (Estimation of parameters characterizing the geological layers by genetic inversion procedure), (182), pp.283–288.
    [Google Scholar]
  6. PriezzhevI.I., L.E.Shmaryan, G.Bejarano
    , 2008, Nonlinear multitrace seismic inversion using neural network and genetic algorithm, - 3rd EAGE St. Petersburg International Conference.
    [Google Scholar]
  7. Priezzhev, I., A.Scollard, and Z.Lu
    , 2014, Regional production prediction technology based on gravity and magnetic data from the Eagle Ford formation, Texas, USA, Denver SEG.
    [Google Scholar]
  8. Priezzhev, I. and P.F.Popova
    , 2010, Seismic inversion and petrophysical geomodelling. Geomodel 2010–12th EAGE science and applied research conference on oil and gas geological exploration and development.
    [Google Scholar]
  9. Veeken, P.C.H., I.I.Priezzhev, L.E.Shmaryan, Y.I.Shteyn, A.Y.Barkov, and Y.P.Ampilov
    , 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]
  10. Veeken, P.C.
    , 2013. Seismic Stratigraphy and depositional facies models. Academic Press.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.201702215
Loading
/content/papers/10.3997/2214-4609.201702215
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