A Comparison of Self-organizing Maps and Hierarchical Cluster Analysis Approaches in Predicting Total Organic Carbon Using Intelligent Systems

Document Type : Research Paper

Authors

1 School of Geology, University College of Science, University of Tehran, Tehran, Iran

2 Department of Geology, Faculty of Natural Science, University of Tabriz, Tabriz, NW, Iran

Abstract

Total organic carbon (TOC) is one of the main parameters for geochemical evaluation of oil and gas source rocks. In this study, we propose a two-step approach to predict total organic carbon content from well log data. Initially, the well log data are classified into a set of electrofacies (EF). The methods used to characterize and identify EF consist of self-organizing maps (SOM) and hierarchical cluster analysis (HCA). The results obtained from both methods are compared and the best method based on cluster validity tests is chosen for clustering petrophysical data into a certain number of EF. Afterwards, the TOC values are estimated from well log data by using individual artificial neural network (ANN) models constructed for each EF. In the second approach, the TOC data are estimated for the total interval by using a similar ANN model regardless of data clustering and EF determination. The results of two prediction methods are compared to each other and also with a third conventional Δlog R technique. The results show that clustering of a formation into specific units (electrofacies) provides better results in TOC prediction compared to the models constructed for the whole dataset as a single cluster. In addition, intelligent systems are more efficient than the previous conventional techniques based on Δlog R method. The proposed methodology is illustrated using a case study of the world’s largest non-associated gas reservoir, i.e. Iran South Pars Gas Field, located in the Persian Gulf.
 

Keywords

References

[1]. نجاری س.، علیزاده ب.، کدخدایی علی.، "تخمین کل کربن آلی (TOC) توسط روش‌های شبکه عصبی مصنوعی و log R ∆ در میدان گازی پارس جنوبی"، بیست و نهمین گردهمایی علوم زمین، سازمان زمین شناسی و اکتشافات معدنی کشور، تهران، ایران، 1389.
[2]. Passey O. R., Moretti F. U. and Stroud J. D., “A practical modal for organic richness from porosity and resistivity logs”, American Association of Petroleum Geologists Bulletin 74, pp.1777-1794. 1990
[3]. Kamali M. R. and Mirshady A. A., Total organic carbon content determined from well logs using Δ log R and neuro-fuzzy techniques. J. Petrol. Sci. Eng. 45, pp. 141–148. 2004.
[4]. Huang Z., Williamson M. A., “Artificial neural network modeling as an aid to source rock characterization”, Marine and Petroleum Geology 13 (2), pp. 227-290. 1996
[5]. Kadkhodaie-Ilkhchi A., Rahimpour-Bonab H. and Rezaee M. R., “A Committee Machine with Intelligent Systems for Estimation of Total Organic Carbon Content from Petrophysical Data: An Example from the Kangan and Dalan Reservoirs in South Pars Gas Field”, Iran. Computers & Geosciences 35, 459-474,2009
[6]. Kashfi M. S., “Greater Persian Gulf Permian–Triassic stratigraphic nomenclature requires study”, Oil and Gas Journal (Tulsa) 6, pp. 36-44,2000
[7]. Ji C. Y., “Land-use classification of remotely sensed data using Kohonen self-organizing feature map neural networks”, Photogrammetric Engineering and Remote Sensing 66, pp. 1451–1460. 2000,
[8]. Vilmann T., Merenyi E. and Hammer B., “Neural maps in remote sensing image analysis”, Neural Networks 16, pp. 389-403. 2003.
[9]. Fayos J. and Fayos C., “Wind data mining by Kohonen neural networks”, PLoS ONE 2, pp. 210. 2007.
[10]. Cassano E. N., Lynch A. H., Cassano J. J. and Koslow M. R., “Classification of synoptic patterns in the western Arctic associated with extreme events at Barrow”, Alaska, USA. Climate Research 30, pp. 83-97. 2006.
[11]. Cole ou T., Poupon M. and Azbe K., “Unsupervised seismic facies classification: a review and comparison of techniques and implementation”, The Leading Edge 22, pp. 942–953, 2003.
[12]. Strecker U. and Uden R., “Data mining of 3D poststack seismic attribute volumes using Kohonen self-organizing maps”, The Leading Edge 21, pp. 1032-1037. 2002.
[13]. Kohonen T., Kaski S. and Lappalainen H., “Self-organized formation of various invariantfeature filters in the adaptive-subspace SOM”, Neural Computation 9, pp. 1321-1344. 1997.
[14]. Mukherjee A., “Self-organizing neural network for identification of natural modes”, The Journal of Computing in Civil Engineering 11 (1), pp. 74-77. 1997.
[15]. Astela A., Tsakovski S., Barbieri P. and Simeonov V., “Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets”, Journal of Water Research 41, pp. 4566-4578, 2007.
[16]. Kohonen T., “Self-Organizing Maps, Springer series in Information Sciences”, New York, Springer-Verlag, Vol. 30, pp. 501, 2001.
[17]. Tan P-N., “Steinbach M. and Kumar V. Introduction to Data Mining”, Pearson Addison Wesley, pp. 769, 2006.
[18]. Bhatt A ., Helle H. B., “Committee neural networks for porosity and permeability prediction from well logs”, Geophysical Prospecting 50, pp. 645-660. 2002.
[19]. Bishop C. M., “Neural Networks for Pattern Recognition”, Clarendon Press, Oxford, pp. 670, 1995.
 
Journal of Petroleum Research
Volume 23, Issue 75 - Serial Number 75
November and December 2013
Pages 117-130

Files

Share

How to cite

Statistics