M Hassanpoor - Petroleum University of Technology, Abadan Faculty of Petroleum Engineering,Department of Petroleum Engineering, Abandan, Iran
S Moradi - Petroleum University of Technology, Abadan Faculty of Petroleum Engineering,Department of Petroleum Engineering, Abandan, Iran
M.K Ghassem Alaskari - Petroleum University of Technology, Ahwaz Faculty of Petroleum Engineering,Department of Petroleum Engineering, Ahwaz, Iran
S Parchekhari - National Iranian South Oil Company, Ahwaz, Iran

Spatial distribution of petrophysiccal properties within the reservoirs is important to provide reliable reservoir description. The most completereservoir description is provided through identification of flow units.This paper suggests intelligent techniques using artificial neural network (ANN), fuzzy logic and neuro-fuzzy to determine flow units from well log data. For this purpose, available routine core and wireline log data from five wells are assembled to find the best intelligent formulation between corederived flow units and well log data. Validation of the predictive capability ofthe models evaluated in one separate cored well (Blind-test). At the finalpart of this study an uncored well was selected for flow unit generalization and prediction. The results show that fuzzy logic derived flow units had better accuracy with respect to other techniques. This comparison showed that fuzzy logiccan be used as the most reliable intelligent technique for flow unit prediction from well log data in uncored wells.