Estimation and modeling of the TOC using hybrid neural network and geostatistical approaches in the one of the Iranian fields

The amount of the Total Organic Carbon (TOC) is one of the most important parameters in geochemical evaluation of hydrocarbon source rocks and subsequent petroleum system modeling. We proposed a three- step approach in predicting and modeling TOC content from well log data. Initially, TOC evaluated for 92 core and cutting samples by Rock-Eval pyrolysis method. In the next step the TOC were predicted using intelligent neural network with back propagation algorithm from well log data. Correlation coefficient between the network output and target data in the training, validation and testing steps for the optimized model is 0.9, 0.88 and 0.91 respectively which indicate the satisfactory approach in predicting TOC. Finally geostatistical methods were used to 3D modeling of this parameter in the field study. The proposed methodology is illustrated using a case study from the world's largest non-associated gas reservoir, the South Pars Gas Field, the Persian Gulf basi