Porosity estimation is one of the essential issues in petroleum industries to distinguish the reservoir characteristics properly. Therefore, it is of importance to predict porosity with the optimum way to reduce the logging tests. In this study, artificial neural network and fuzzy logics are considered efficient techniques to predict the Asmari formation’s porosity. The results of porosity estimation by intelligent neuro-phase method showed the ability of this method to estimate in complex conditions in Mansouri oilfield. Preparing data before training the neural network increases the power of the network in recognizing the appropriate pattern. In estimating the porosity in the Asmari reservoir of Mansouri field, gamma, acoustic, neutron and density and diameter measurements have a more influential role. Selecting the appropriate architecture for the neuro-phase network is effective in achieving more accurate results. This architecture includes selecting the type and number of membership functions for the inputs and the training algorithm with the appropriate number of iteration steps. The best estimation results by assigning four Gaussian membership functions to gamma image data, two Gaussian membership functions to each of the audio and neutron data, and three Gaussian membership functions to density image data and creating 40 laws in the data space. Inputs were obtained using a hybrid training algorithm. The average error of estimating porosity by the neuro-phase method in well C of Mansouri field is 1.28% in the validation data set, representing a correlation coefficient of 92.5% between the porosity extracted from the fuzzy neuro-fuzzy network and the porosity of the core.