A Robust Methodology for Prediction of DT Wireline Log

Dt log is one of the most frequently used wireline logs to determine compression wave velocity. this log is commonly used togain insight into the elastic and petrophysical parameters of reservoir rocks. acquisition of dt log is, however, a very expensive andtime consuming task. thus prediction of this log by any means can be a great help by decreasing the amount of money that needs tobe allocated for acquisition. support vector machine (svm) is one of the best artificial intelligence techniques proven to be a reliablemethod in the prediction of various real world problems. the aim of this paper is to use svm to predict the dt log data of a welllocated in the southern oilfields of iran. by comparing the results of svm with those obtained by a back propagation neuralnetwork (bpnn) we were able to verify the accuracy of svm in the prediction of p-wave velocity. hence, this method isrecommended as a cost effective tool in the prediction of p- wave velocity.