Estimating the reservoir parameters is one of the important factors in the evaluation of oil and gas reservoirs. One of the most important parameters of the reservoir for reservoir modeling is water saturation. The mistake in calculating it can cause a lot of damages. With core of wells, water saturation can be achieved; but there is no clear core or even a well, and there is a need to estimate water saturation in some parts. In this study, we used the support vector regression method to estimate water saturation that is a type of learning machine application that has been able to solve the problems of high dimensionality. The method is that some wells data were introduced to train this method and the real water saturation value was calculated as the objective function to obtain a function for water saturation estimation. It was used to obtain the best function from two different kernel functions.