A committee neural network for prediction of normalized oil content from well log data: An example from South Pars Gas Field, Persian Gulf

Abstract

Normalized oil content (NOC) is an important geochemical factor for identifyingpotential pay zones in hydrocarbon source rocks. The present study proposes an optimaland improved model to make a quantitative and qualitative correlation between NOC andwell log responses by integration of neural network training algorithms and thecommittee machine concept. This committee machine with training algorithms (CMTA)combines Levenberg-Marquardt (LM), Bayesian regularization (BR), gradient descent(GD), one step secant (OSS), and resilient back-propagation (RP) algorithms. Each ofthese algorithms has a weight factor showing its contribution in overall prediction. Theoptimal combination of the weights is derived by a genetic algorithm. The method isillustrated using a case study. For this purpose, 231 data composed of well log data andmeasured NOC from three wells of South Pars Gas Field were clustered into 194modeling dataset and 37 testing samples for evaluating reliability of the models. Theresults of this study show that the CMTA provides more reliable and acceptable resultsthan each of the individual neural networks differing in training algorithms. Also CMTAcan accurately identify production pay zones (PPZs) from well logs.