Predicting carbonate permeabilities from wireline logs using a back-propagation neural network

This study explores the applicability of using Neural Networks to aid in the determination of carbonate permeability from wireline logs. Resistivity, interval transit time, neutron porosity, and bulk density logs from Texaco's Stockyard Creek field were used as input to a specially designed neural network to predict core permeabilities in this carbonate reservoir. Also of interest was the comparison of the neural network's results to those of standard statistical techniques. The process of developing the neural network for this problem has shown that a good understanding of the data is required when creating the training set from which the network learns. This network was trained to learn core permeabilities from raw and transformed log data using a hyperbolic tangent transfer function and a sum of squares global error function. Also, it required two hidden layers to solve this particular problem. The results obtained indicate that a back-propagation network can recognize permeability in carbonate rocks from wireline logs with an accuracy of 96 percent. This compares to standard regression techniques which produce correlation coefficients of .61 for linear regression, .70 for polynomial regression, and .76 for multi-variate analysis. Based on the success experienced in this work, we feel confident that even more significant applications using neural networks are possible.