TY - JOUR

T1 - Integration of gustafson-kessel algorithm and ohonen's self-organizing maps for unsupervised clustering of seismic attributes

AU - Eftekharifar, Mehdi

AU - Riahi, M. Ali

AU - Kharrat, Riyaz

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

KW - Complex seismic attributes

KW - Fuzzy logic

KW - Fuzzy self- organizing maps

KW - Gustafson-kessel algorithm

KW - Inversion

KW - Kohonen's self-organizing maps (som)

KW - Reservoir characterization

KW - Unsupervised clustering

UR - http://www.scopus.com/inward/record.url?scp=70350180276&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:70350180276

VL - 18.2009

SP - 315

EP - 328

JO - Journal of seismic exploration

JF - Journal of seismic exploration

SN - 0963-0651

IS - 4

ER -