Facies identification from well logs: A comparison of discriminant analysis and naive Bayes classifier

The performance of a naive Bayes classifier is compared with a well-established statistical classification approach, linear discriminant analysis, by considering core and log data from marine-eolian sediments. The results indicate that both methods perform adequately, and the Gaussian naive Bayes classifier provides estimates as good as those based on the linear discriminant analysis for the given data set. Quadratic discriminant analysis, a more conventional Bayesian analysis, and kemel-based density estimation methods perform unexpectedly poor, probably because of overfitting. We conclude that the normal distribution is appropriate to fit the distribution of log readings in the present data, and the simplifications of naive Bayes provide a robust, simple approach for facies identification. (c) 2006 Elsevier B.V. All rights reserved.