A committee machine with intelligent systems for estimation of total organic carbon content from petrophysical data: An example from Kangan and Dalan reservoirs in South Pars Gas Field, Iran

Authors:
Ali Kadkhodaie-Ilkhchi;Hossain Rahimpour-Bonab;Mohammadreza Rezaee
Affiliations:
Department of Geology, College of Science, University of Tehran, Tehran, Iran;Department of Geology, College of Science, University of Tehran, Tehran, Iran;Department of Geology, College of Science, University of Tehran, Tehran, Iran and Department of Petroleum Engineering, Curtin University of Technology, Perth, Australia
Venue:
Computers & Geosciences
Year:
2009

Citing 4
Cited 1

Neural networks and the bias/variance dilemma

Neural Computation
Recognition of gestures in Arabic sign language using neuro-fuzzy systems

Artificial Intelligence
Neural Networks: A Comprehensive Foundation (3rd Edition)

Neural Networks: A Comprehensive Foundation (3rd Edition)
A committee machine with empirical formulas for permeability prediction

Computers & Geosciences

Artificial neural network modeling and cluster analysis for organic facies and burial history estimation using well log data: A case study of the South Pars Gas Field, Persian Gulf, Iran

Computers & Geosciences

Quantified Score

Hi-index	0.00

Visualization

Abstract

Total organic carbon (TOC) content present in reservoir rocks is one of the important parameters, which could be used for evaluation of residual production potential and geochemical characterization of hydrocarbon-bearing units. In general, organic-rich rocks are characterized by higher porosity, higher sonic transit time, lower density, higher @c-ray, and higher resistivity than other rocks. Current study suggests an improved and optimal model for TOC estimation by integration of intelligent systems and the concept of committee machine with an example from Kangan and Dalan Formations, in South Pars Gas Field, Iran. This committee machine with intelligent systems (CMIS) combines the results of TOC predicted from intelligent systems including fuzzy logic (FL), neuro-fuzzy (NF), and neural network (NN), each of them has a weight factor showing its contribution in overall prediction. The optimal combination of weights is derived by a genetic algorithm (GA). This method is illustrated using a case study. One hundred twenty-four data points including petrophysical data and measured TOC from three wells of South Pars Gas Field were divided into 87 training sets to build the CMIS model and 37 testing sets to evaluate the reliability of the developed model. The results show that the CMIS performs better than any one of the individual intelligent systems acting alone for predicting TOC.