Seismic Attributes Similarity in Facies Classification

Chapter
Part of the Studies in Big Data book series (SBD, volume 40)

Abstract

Seismic attributes are one of the component of reflection seismology. Formerly the advances in computer technology have led to an increase in number of seismic attributes and thus better geological interpretation. Nowadays, the overwhelming number and variety of seismic attributes make the interpretation less unequivocal and can lead to slow performance. Using the correlation coefficients, similarities and hierarchical grouping the analysis of seismic attributes was carried out on several real datasets. We try to identify key seismic attributes (also the weak ones) that help the most with machine learning seismic attribute analysis and test the selection with Random Forest algorithm. Obtained quantitative factors help with the overall look at the data. Initial tests have shown some regularities in the correlations between seismic attributes. Some attributes are unique and potentially very helpful with information retrieval while others form non-diverse groups. These encouraging results have the potential for transferring the work to practical geological interpretation.

Keywords

Seismic attributes Geophysics Correlation Similarity Machine learning 

Notes

Acknowledgements

Seismic data from the Kłodawa-Ponetów–Wartkowice area was acquired for the BlueGas-JuraShale project (BG1/JURASHALE/13) funded by the Polish National Centre for Research and Development (NCBiR). San Leon Energy is thanked providing access to seismic data from the Nida Trough. We would also thank to Paradigm \(\circledR \) for providing academic software license for seismic attributes extraction and to the authors and developers of Python, NumPy, Matplotlib and ObsPy.

References

  1. 1.
    Zbigniew Kasina. Metodyka badan sejsmicznych. Polish. Wydaw. Instytutu GSMiE PAN [Gospodarki Surowcami Mineralnymi i Energia Polskiej Akademii Nauk], 1998. 289 pp. isbn: 83-87854-20-4Google Scholar
  2. 2.
    Chopra, S., Marfurt, K.J.: Seismic attributes - a historical perspective. Geophysics 70(5), 3SO–28SO (2005).  https://doi.org/10.1190/1.2098670CrossRefGoogle Scholar
  3. 3.
    Chopra, S., Marfurt, K.J.: Seismic attributes for prospect identification and reservoir characterization. Soc. Explor. Geophys. (2007).  https://doi.org/10.1190/1.9781560801900
  4. 4.
    Barnes, A.: Too many seismic attributes? vol. 31 (Landmark Graphics Corporation, Colorado, USA, 2006)Google Scholar
  5. 5.
    Barnes, A.E.: Attributes for automating seismic facies analysis. SEG Tech. Progr. Expand. Abstr 2000. Soc. Explor. Geophys. 1, 553–556 (2000).  https://doi.org/10.1190/1.1816121CrossRefGoogle Scholar
  6. 6.
    Qi, J., et al.: Semisupervised multiattribute seismic facies analysis. Interpretation 4(1), SB91–SB106 (2016).  https://doi.org/10.1190/INT-2015-0098.1CrossRefGoogle Scholar
  7. 7.
    Coléou, T., Poupon, M., Azbel, Kostia: Unsupervised seismic facies classification: a review and comparison of techniques and implementation. Lead. Edge 22(10), 942–953 (2003).  https://doi.org/10.1190/1.1623635CrossRefGoogle Scholar
  8. 8.
    Kursa, M.B., Rudnicki, W.R.: Feature Selection with the- BorutaPackag. J. Stat. Softw. 36(11) (2010).  https://doi.org/10.18637/jss.v036.i11
  9. 9.
    Kursa, M.B., Jankowski, A., Rudnicki, W.R.: Boruta – a system for feature selection. Fundam. Inf. 101(4), 271–285 (2010).  https://doi.org/10.3233/FI-2010-288. ISSN: 0169-2968MathSciNetCrossRefGoogle Scholar
  10. 10.
    Krzywiec, P., et al. Control of salt tectonics on mesozoic unconventional petroleum system of the central mid-polish trough. In: AAPG Annual Convention and Exhibition 2015, Denver, USA (2015)Google Scholar
  11. 11.
    Jain, A.K., Murty, M.N., Flynn, P.J.: Data clustering: a review. ACM Comput. Surv. 31(3), 264–323 (1999).  https://doi.org/10.1145/331499.33150CrossRefGoogle Scholar
  12. 12.
    Cracknell, Matthew J., Reading, Anya M.: Geological mapping using remote sensing data: A comparison of five machine learning algorithms, their response to variations in the spatial distribution of training data and the use of explicit spatial information. Comput. Geosci. 63, 22–33 (2014).  https://doi.org/10.1016/j.cageo.2013.10.008CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Institute of Computer ScienceWarsaw University of TechnologyWarszawaPoland
  2. 2.Institute of Geological SciencesPolish Academy of SciencesWarsawPoland

Personalised recommendations