A New Method to Classification of Total Organic Carbon by Petrophysical Logs in Australia

Abstract

Total Organic Carbon (TOC) is an importance parameter in the assessment of rock sources. By evaluating this parameter, we can estimate the total amount of hydrocarbons in the rocks. The most common method for measuring TOC is the use of cores obtained from drilled wells. This is a costly and time-consuming process and, in addition to the expenditure of coring, will cost a lot of maintenance. Over the past few years, extensive studies have been carried out to estimate TOC using less costly methods, which will be discussed in more details in the introduction. Modern and low-cost methods help to inspect reservoirs with high exploratory risk like gas shale reservoirs. In this paper, it was tried to make a correlation between conventional Petrophysical logs and TOC using the neural network in one well in western Australia. By encoding the initial data and categorizing them in the neural network, we finally conclude that it is possible to obtain a good accuracy of classification of hydrocarbon content.