We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 November 2024
Reseach Article

Core Porosity Estimation through Different Training Approaches for Neural Network: Back-Propagation Learning vs. Genetic Algorithm

by Mojtaba Asoodeh, Parisa Bagheripour
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 63 - Number 5
Year of Publication: 2013
Authors: Mojtaba Asoodeh, Parisa Bagheripour
10.5120/10461-5172

Mojtaba Asoodeh, Parisa Bagheripour . Core Porosity Estimation through Different Training Approaches for Neural Network: Back-Propagation Learning vs. Genetic Algorithm. International Journal of Computer Applications. 63, 5 ( February 2013), 11-15. DOI=10.5120/10461-5172

@article{ 10.5120/10461-5172,
author = { Mojtaba Asoodeh, Parisa Bagheripour },
title = { Core Porosity Estimation through Different Training Approaches for Neural Network: Back-Propagation Learning vs. Genetic Algorithm },
journal = { International Journal of Computer Applications },
issue_date = { February 2013 },
volume = { 63 },
number = { 5 },
month = { February },
year = { 2013 },
issn = { 0975-8887 },
pages = { 11-15 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume63/number5/10461-5172/ },
doi = { 10.5120/10461-5172 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T21:13:20.413510+05:30
%A Mojtaba Asoodeh
%A Parisa Bagheripour
%T Core Porosity Estimation through Different Training Approaches for Neural Network: Back-Propagation Learning vs. Genetic Algorithm
%J International Journal of Computer Applications
%@ 0975-8887
%V 63
%N 5
%P 11-15
%D 2013
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Porosity of hydrocarbon bearing formations is a crucial parameter for reservoir characterization, reserve estimation, planning for completion, and geomechanical and geophysical studies. Accurate determination of porosity from laboratory core analysis is highly cost, time, and people intensive. Therefore, the quest for a rapid, cost-effective, and efficient method of determining porosity is inevitable. Conventional well log data are available in all wells and provide cheap continuous information. In this study, an improved strategy was followed to formulate conventional well log data (inputs) into core porosity (output) using the genetic optimized neural network (GONN). Firstly, back-propagation (BP) algorithm, the conventional learning method of neural network, was used to extract the formulation between inputs/output data space. Then, neural network was trained through the use of genetic algorithm (GA). Comparison between BP learning and GA demonstrated the effectiveness of GONN. It was deduced that GA enforces the performance function of neural network to converge to global minimum contrary to BP which frequently traps in local minima.

References
  1. Al-Qahtani, F. A. 2000. Porosity Distribution Prediction Using Artificial Neural Networks. College of Engineering and Mining Recourses, West Virginia University, M. Sc. Thesis, 1-3.
  2. Asoodeh, M. , Bagheripour, P. 2012. Prediction of Compressional, Shear, and Stoneley Wave Velocities from Conventional Well Log Data Using a Committee Machine with Intelligent Systems. Journal of Rock Mechanics and Rock Engineering 45, 45-63.
  3. Mohaghegh, S. D. 2000. Virtual-intelligence applications in petroleum engineering: part 1-Artificial Neural Network. Distinguished Author Series articles, SPE 58046.
  4. MATLAB user's guide. 2011. Fuzzy logic, Neural Network & GA and Direct Search Toolboxes, MATLAB CD-ROM, by the Mathworks, Inc.
  5. Asoodeh, M. , Bagheripour, P. 2012. Estimation of Bubble Point Pressure from PVT Data Using a Power-Law Committee with Intelligent Systems. Journal of Petroleum Science and Engineering 90-91, 1-11.
  6. Kononen, V. 2005. Gradient descent for symmetric and asymmetric multiagent reinforcement learning. Web Intell. Agent Syst. 3, 17–30.
  7. Burney, S. M. A. , Jilani, T. A. , Ardil, C. 2004. Levenberg–Marquardt Algorithm for Karachi Sock Exchange Share Rates Forecasting. Trans. Eng. Comput. Technol. 3, 1305–1313.
  8. Demuth, H. , Beale, M. 2002. Neural Network Toolbox, User's Guide (Version 4). The Mathworks Inc.
  9. Baird, L. , Moore, A. 1999. Gradient Descent for General Reinforcement Learning. Adv. Neural Inf. Process Syst. 11, 968–974.
  10. Bishop, C. M. 1995. Neural Networks for Pattern Recognition. Clarendon Press, Oxford, p. 670.
  11. Riedmiller, M. , Braun, H. 1993. A direct adaptive method for faster back-propagation learning: the RPROP algorithm. Proc. IEEE Conf. on Neural Networks.
  12. MacKay, D. J. C. 1992. A practical Bayesian framework for back-propagation networks. Neural Comput 4, 448–472.
  13. Battiti, R. 1992. First and second order methods for learning: between steepest descent and Newton's method. Neural Comput 4 (2), 141–166.
Index Terms

Computer Science
Information Sciences

Keywords

Back-Propagation Genetic Algorithm Genetic Optimized Neural Network Core Porosity Conventional Well Log Data