This paper introduces a successful application of neural networks in predicting porosity, fluid saturation and identifying lithofacies using well log data. This technique utilizes the prevailing unknown nonlinear relationship in data between well logs and the reservoir properties, to determine accurately certain petrophysical properties of the reservoir rocks under different compaction conditions. In heterogeneous reservoirs classical methods face problems in determining the relevant petrophysical parameters accurately. Applications of artificial intelligence have recently made this challenge a possible practice. This paper presents successful achievement in applying two trained NN, one for porosity prediction and second training for one for water saturation using 5 log data inputs: (Gamma Ray)GR, (Laterolog Deep)LLD, (density) RHOB, (Neutron) NPHI.