Separating Well Log Data to Train Support Vector Machines for Lithology Prediction in a Heterogeneous Carbonate Reservoir

Abstract

The prediction of lithology is necessary in all areas of petroleum engineering. This means that to design a project in any branch of petroleum engineering, the lithology must be well known. Support vector machines (SVM's) use an analytical approach to classification based on statistical learning theory, the principles of structural risk minimization, and empirical risk minimization. In this research, SVM classification method is used for lithology prediction from petrophysical well logs based on petrographic studies of core lithology in a heterogeneous carbonate reservoir in southwestern Iran. Data preparation including normalization and attribute selection was performed on the data. Well by well data separation technique was used for data partitioning so that the instances of each well were predicted against training the SVM with the other wells. The effect of different kernel functions on the SVM performance was deliberated. The results showed that the SVM performance in the lithology prediction of wells by applying well by well data partitioning technique is good, and that in two data separation cases, radial basis function (RBF) kernel gives a higher lithology misclassification rate compared with polynomial and normalized polynomial kernels. Moreover, the lithology misclassification rate associated with RBF kernel increases with an increasing training set size.