ARTICLE

Integration of Gustafon-Kessel algorithm and Kohonen’s self-organizing maps for unsupervised clustering of seismic attributes

MEHDI EFTEKHARIFAR1 M. ALI RIAHI2 R. KHARRAT3
Show Less
1 Petroleum University of Technology (IFP-School France). mehdieftekharifar@gmail.com,
2 Institute of Geophysics, University of Tehran, P.O. Box 14155-6466, Tehran, Iran. mariachi@ut.ac.ir,
3 Petroleum University of Technology, Tehran, Iran. kharrat@put.ac.ir,
JSE 2009, 18(4), 315–328;
Submitted: 5 January 2008 | Accepted: 8 June 2009 | Published: 1 October 2009
© 2009 by the Authors. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

Eftekharifar, M., Riahi, M.A. and Kharrat, R., 2009. Integration of Gustafson-Kessel algorithm and Kohonen’s self-organizing maps for unsupervised clustering of seismic attributes. Journal of Seismic Exploration, 18: 315-328. The goal of different methods for clustering of seismic attributes has been to analyze the discrimination ability of the chosen set of attributes. Kohonen clustering networks or Kohonen’s self organizing maps are well known for cluster analysis (unsupervised learning). This class of algorithms is a set of heuristic procedures that suffers from some major problems. In this paper we propose the use of an unsupervised method by integrating the fuzzy c-means clustering and Gustafson-Kessel algorithms into the learning rate and updating strategies of the Kohonen clustering network. Using a new fuzzy calibration method, the different attribute classes are calibrated to lithology classes and the appropriate attributes and classes are determined. In this paper we propose a robust clustering algorithm which can be quality-controlled by using fuzzy modeling. That means using the clustering results, the available but limited log data is rebuilt after clustering to see the performance of the clustering technique. Classification and modeling results tested on a real data set show reasonable accuracy when compared to well logs.

Keywords
unsupervised clustering
Kohonen’s self-organizing maps (SOM)
fuzzy self-organizing maps
fuzzy logic
Gustafson-Kessel algorithm
complex seismic attributes
reservoir characterization
inversion
References
  1. Babuska, R., 1996. Fuzzy Modeling and Identification. PhD thesis, Dept. of Control Engineering,
  2. Delft University of Technology, Delft, The Netherlands.
  3. Bezdek, J.C., 1981; Pattern Recognition with Fuzzy Objective Function Algorithms. Plenum Press,New York.
  4. Tsao, E.C.-K., Bezdek, J.C. and Pal, N.R., 1992. Fuzzy Kohonen Clustering Networks. IEEE:1035-1043.
  5. Dubes, R. and Jain, A., 1988. Algorithms that Cluster Data. Prentice Hall, Englewood Cliffs.
  6. Duda, R. and Hart, P., 1973. Pattern Classification and Scene Analysis, Wiley & Sons, New York.
  7. Gustafson, D.E. and Kessel, W.C., 1979. Fuzzy clustering with a fuzzy covariance matrix. In: ProcIEEE CDC, San Diego, CA: 761-766.
  8. Hartigan, J., 1975. Clustering Algorithms. Wiley & Sons, New York.
  9. Hoppner, F., Kalwoon, F. and Kruse, R., 1997. Fuzzy Clustering Analysis. Vieweg Verlag,Braunschweig, Germany.
  10. Hu, W., Xie, D., Tan, T. and Maybank, S., 2004. Learning activity patterns using fuzzyself-organizing neural network. IEEE Trans. Syst. Man. Cybern B, 34: 1618-1626.
  11. Huntsberger, T. and Ajjimarangsee, P., 1989. Parallel self-organizing feature maps for unsupervisedpattern recognition, Internat. J. Gen. Systems, 16: 357-372.
  12. Kohonen, T., 1989. Self-Organization and Associative Memory, 3rd Ed. Springer-Verlag, Berlin.
  13. Lippman, R., 1987. An Introduction to Neural Computing, IEEE ASSP Magazine, April: 4-22.328 EFTEKHARIFAR, RIAHI & KHARRAT
  14. Pao, Y.H., 1989. Adaptive Pattern Recognition and Neural Networks. Addison-Wesley, Reading.
  15. Taner, M.T., 1997. Kohonen’s Self Organizing Network with 'Conscience', Rock Solid ImagesTechnical Report.
  16. Taner, M.T., 2000. Calibration of Self-Organized Map Clusters. November, Rock Solid ImagesTechnical Report.
  17. Taner, M.T., 2002. Principal Component Analysis Neural Networks; Linear and Non-Linear,January, Rock Solid Images Technical Report.
  18. Tou, J. and Gonzalez, R., 1974. Pattern Recognition Principles. Addison-Wesley, Reading.
  19. Wang, L.X., 1996. A Course In Fuzzy Systems and Control. Prentice Hall, Englewood Cliffs.
Share
Back to top
Journal of Seismic Exploration, Electronic ISSN: 0963-0651 Print ISSN: 0963-0651, Published by AccScience Publishing