The lack of information for reservoir characterization has been a common problem nowadays due to the current economic limitations on companies' capital expenses. Therefore, the reservoir engineer has to fully exploit all available data and estimate the unavailable reservoir characteristics. For lack of core data, the porosity is usually used to estimate the permeability through classical correlations. However, predicting permeability from porosity only and using classical relationships becomes unreliable due to lithology and pore geometry effects. The objective of this study is to test the integration between Flow Zone Indicator (FZI), Artificial Neural Network (ANN), and Convergent Interpolation (CI) techniques to enhance the Tortonian reservoir description in the Gamma oil field using the data of one exploratory well and four appraisal wells.