Full text loading...
-
Petrophysical Property Parameters Prediction of Reservoirs Based on the Kernel-Bayes Discriminant Analysis
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 78th EAGE Conference and Exhibition 2016, May 2016, Volume 2016, p.1 - 5
Abstract
Reservoir physical parameters are the main parameters to characterize the reservoir. Therefore, it is necessary to estimate reservoir physical parameters reasonably and effectively. However, many influence factors and their complex relationships bring about great difficulties to the accurate prediction of reservoir petrophysical parameters. We propose a novel predicted method based on the Kernel-Bayes discriminant analysis. The proposed method does not assume that the predicted parameter follows a specific distribution. Besides, the conditional probability function is obtained by nonparametric estimation method. The proposed novel method not only can predict petrophysical property parameters such as porosity, shale content and water saturation, but also provide the posterior probability that could be applied to analyze the uncertainty of predicted results quantitatively. The test of field data indicates that the proposed method can predict the reservoir petrophysical parameters effectively and efficiently.