Exploration Geophysics Exploration Geophysics Society
Journal of the Australian Society of Exploration Geophysicists
RESEARCH ARTICLE

Seismic pattern recognition based upon Hopfield Neural Networks

Rafael Banchs 1 Oscar Rondon 2 3
+ Author Affiliations
- Author Affiliations

1 Signal Processing and Communications Department, Universitat Politècnica de Catalunya, Campus Nord, D4-100, Barcelona 08034, Spain.

2 Snowden Group, 87 Colin Street, West Perth, Perth, Western Australia, Australia, WA 6005, Australia.

3 Corresponding author. Email: orondon@snowdengroup.com

Exploration Geophysics 38(4) 220-224 https://doi.org/10.1071/EG07024
Submitted: 19 September 2006  Accepted: 2 October 2007   Published: 6 December 2007

Abstract

A classification method based on the use of seismic attribute pattern recognition by means of Hopfield Neural Networks is presented. The method is suitable for exploration projects and it can be used to simultaneously perform the analysis of several references or classes and for constructing seismic similarity maps or volumes. First, a brief description of Hopfield Neural Networks and their operational principles is presented, and the most relevant issues of the proposed classification methodology are described. Then, the method is demonstrated by using a synthetic dataset and two real case studies, illustrating the potential of the method as a useful tool for exploration geophysics and reservoir characterisation.

Key words: pattern recognition, Hopfield neural networks, seismic attributes, seismic similarity, classification.


Acknowledgments

We thank Dr Juan Jimenez for his valuable help with the geological description of the regions analysed in the case studies, as well as the interpretation of some of the results.


References

Bruck, J.,, 1990, On the convergence properties of the Hopfield model: Proceedings of the IEEE 78, 1579–1585.
CrossRef |

Coléou, T. R., Poupon, M., and Azbel, K., 2003, Unsupervised seismic facies classification: a review and comparison of techniques and implementation: The Leading Edge 22, 942–953.
CrossRef |

Haykin S., 1999, Neural Networks: a Comprehensive Foundation, Pearson Prentice Hall.

Hopfield, J., 1982, Neural networks and physical systems with emergent collective computational abilities: Proceedings of the National Academy of Science of the U.S.A. 79, 2554–2558.
CrossRef |

Jiménez, J., Michelena, R., and Peinado, A., 1999, Facies recognition using wavelet-based fractal analysis on compressed seismic data: 69th Annual International Meeting: Soc. Explor. Geophys., Expanded Abstracts , 1922–1925.
CrossRef |

Johnston, D. H., 1993, Seismic attribute calibration using neural networks: 63rd Annual International Meeting: Soc. Expl. Geophys. Expanded Abstracts 93, 250–253.


Matteucci G. , 1996, Seismic attribute analysis and calibration: a general procedure and a case study: Annual Meeting Abstracts: Society of Exploration Geophysicists, 373–376.

Michelena, R., González, E., and Capello, M.,, 1998, Similarity analysis: a new tool to summarize seismic attributes information: The Leading Edge 17, 545–548.
CrossRef |

Personnaz, L., Guyon, I., and Dreyfus, G., 1985, Information storage and retrieval in spin-glass like neural networks: Journal de Physique 46, L359–L365.


Rondon, O., and Banchs, R., 2007, Seismic similarity analysis through self-organising maps: Exploration Geophysics 38, 184–188.
CrossRef |

Strecker, U., and Uden, K., 2002, Data mining of 3D post-stack seismic attribute volumes using Kohonen self-organizing maps: The Leading Edge 21, 1032–1037.
CrossRef |



Export Citation