Scientific Quarterly Journal of Geosciences

Scientific Quarterly Journal of Geosciences

Porosity Assessment of Kangan Gas Formation in South Pars Hydrocarbon Field by Application of Committee Machine Composed of Single Artificial Neural Networks Trained using Regularization Method

Document Type : Original Research Paper

Authors
A. Kamkar Rouhani
M. Zakeri
Faculty of Mining, Petroleum and Geophysics, Shahrood University of Technology, Shahrood, Iran
10.22071/gsj.2012.54513
Abstract
In order to obtain more accurate results from application of the method of artificial neural networks, instead of selection of the best network determined by trial and error process, we suitably combine the results of several networks that is called committee machine, to reduce the error, and thus, increasing the accuracy of the output results. In this research, ensemble combination of single artificial neural networks has been used in order to estimate the effective porosity of Kangan gas reservoir rock in South Pars hydrocarbon field. To achieve this goal, well logging data of 4 wells in the area at the depth interval corresponding to Kangan formation were used. Acoustic, density, gamma ray and neutron porosity well log data were assigned as the input of the networks while the effective porosity data were considered as the output of the networks. Back- propagation single neural networks having different structures were trained using regularization method and their results were assessed. Then, the networks with the best results, i.e. contained minimum mean of squares of errors in the test step, were selected for making ensemble combinations. To determine the weighting coefficients of the networks in the linear ensemble combinations, we applied three methods of simple averaging, Hashem’s optimal linear combination and non-analytical optimal linear combination employing genetic algorithm, and their results were compared. The best ensemble combination, in which we had the maximum reduction in mean of squares of errors of the test step compared to the best single neural network, was an optimal linear four-network combination obtained by using genetic algorithm optimization method. This best ensemble combination, compared to the best single neural network, reduced the mean of squares of errors in the training and test steps 3.6%  and 11.2%, respectively.
Keywords
Kangan Formation
porosity
Well Logs
Artificial Nneural Network
Regularization Training Method
Committee Machine
Ensemble combination
Genetic algorithm
References
Bhatt, A. & Helle, H. B., 2002- Committee neural networks for porosity and permeability prediction from well logs, Geophysical Prospecting, 50: 645-660.
Bhatt, A., 2002- Reservoir properties from well logs using neural networks, PhD thesis, Department of Petroleum Engineering and Applied Geophysics, Norwegian University of Science and Technology.
Chen, C. H. & Lin, Z. S., 2006- A committee machine with empirical formulas for permeability prediction, Computer & Geosciences, 32: 485-496.
Demuth, H. & Beale, M., 2002- Neural network toolbox user's guide of MATLAB, Version 4, Online on http://www.mathworks.com/.
Hashem, S., 1993- Optimal linear combination of neural networks, PhD thesis, School of Industrial Engineering, Purdue University.
Hashem, S., 1997- Optimal linear combination of neural networks, Neural Networks, 10: 599-614.
Hashem, S., Shmeiser, B. & Yih, Y., 1994- Optimal linear combination of neural networks: An overview, School of Industrial Engineering, Purdue University.
MathWorksTM, 2007- Genetic algorithm and direct search toolbox 2 user's guide of MATLAB, Online on http://www.mathworks.com/.
Sharkey, A., Sharkey, N., Gerecke, U. & Chandroth, G. O., 2000- The "test and select" approach to ensemble combination. In: Kittler J. & Roli F. (eds.) Multiple classifier systems.  Springer-Verlag, Inc. PP30-44.
 
 
Scientific Quarterly Journal of Geosciences
Volume 21, Issue 83
Autumn 2012
Pages 33-40