A Porosity Estimation in a Hydrocarbon Reservoir Using Multiple Networks Systems

Document Type : Research Paper

Authors

1 . Expert of Geophysics, Geological Survey of Iran (GSI)

2 Faculty of Mining, Petroleum and Geophysics, Shahroud University of Technology

Abstract

Multiple networks systems have been proposed for the purpose of decreasing the error and increasing the accuracy of the results of artificial neural network (ANN) method. In these systems, the results of several single ANN’s, which are trained solely and separately, are combined using a suitable method. In this work, the effective porosity in one of hydrocarbon reservoirs of giant Southern Pars field is estimated using multiple networks systems. Single ANN’s trained using early stopping back propagation (BP) method are used as the components of multiple networks systems. Well logging data acquired from 4 wells in the field at the depth interval corresponding to Kangan formation are used. Acoustic, density, gamma ray, and neutron porosity well log data are considered as the inputs of the networks and the effective porosity data are assigned as the output of the networks. The ensemble combination of networks, which have a parallel structure, are applied for making multiple networks systems. The results show that suitable ensemble combinations improve the results of the ANN’s trained using early stopping BP method. The best obtained ensemble combination is a three-network combination compared to the best obtained single ANN, which reduces the mean of squares of errors (MSE) of porosity prediction in the training and test steps by 14.7% and 12.5% respectively.

Keywords

References

[1]. حسنی پاک ع.ا.، شرف‌الدین م.، تحلیل داده‌های اکتشافی، انتشارات دانشگاه تهران، 0831.
[2]. Bhatt A., Reservoir properties from well logs using neural networks, PhD thesis, Department of Petroleum Engineering and Applied Geophysics, Norwegian University of Science and Technology, Norway, 2002.
[3]. Bhatt A., Helle H. B., “Committee neural networks for porosity and permeability prediction from well logs”, Geophysical Prospecting., Vol. 50, pp. 645-660, 2002.
[4]. Hashem Sh., Optimal linear combinations of neural networks, PhD thesis, School of Industrial Engineering, Purdue University, America, 1993.
[5]. Hashem Sh., Schmeiser B. and Yih Y., Optimal linear combinations of neural networks: an overview, School of Industrial Engineering, Purdue University, America, 1994.
[6]. Sharkey A., Sharkey N., Gerecke U. and Chandroth G. O., “The “test and select” approach to ensemble combination”, in: Kittler J., Roli F. (Eds.), Multiple Classifier Systems, Lecture Notes in Computer Science, Springer-Verlag, Inc., pp. 30-44, 2000.
[7]. Fung Ch. Ch., Wong K. W. and Eren H., “Modular artificial neural network for prediction of petrophysical properties from well log data”, IEEE transaction on instrumentation and measurement, Vol. 46, pp. 1295-1299, 1997.
[8]. Chen Ch. H., Lin Z. Sh., “A committee machine with empirical formulas for permeability prediction”, Computer & Geosciences., Vol. 32, pp. 485-496, 2006.
[9]. Demuth H., Beale M. and Hagan M., Neural network toolboxTM 6 user›s guid, MATLAB Software, www.mathworks.com, 2009.
[10]. The Math WorksTM, Genetic algorithm and direct search toolbox 2 user›s guide, MATLAB Software, www.mathworks.com, 2007.
[11]. افشارحرب ع.، زمین‌شناسی نفت، انتشارات دانشگاه پیام نور، 1381.
[12] رحیمی م.، تعبیر و تفسیر لرزه‌ای ناحیه پارس جنوبی در افق‌های آسماری، جهرم، سروک، داریان، فهلیان، سورمه، کنگان، نار و فراقون، مدیریت اکتشاف شرکت ملی نفت ایران، 1381.
[13] زارعی س.، موحد ب.، باقری ع.م.، مردانی ع.، ارزیابی تراوایی سازند کنگان با استفاده از داده‌های نگار CMR و مغزه در میدان پارس جنوبی، بیست و ششمین گردهمایی علوم زمین‌شناسی، تهران، ایران، 1386.
Journal of Petroleum Research
Volume 23, Issue 74 - Serial Number 74
September and October 2013
Pages 109-125

Files

Share

How to cite

Statistics