Implementation of numerical simulations for field development optimization can be overly demanding in terms of their time and manpower requirements. To overcome these problems, a methodology has been developed that can be used to predict production performance of a given field and perform field development studies with nominal manpower and computational requirements. Artificial neural networks (ANN) are used for development of expert systems for prediction of instantaneous and cumulative gas and water production, as well as for reservoir property prediction. A commercial reservoir simulator is employed for generation of database for training, validation and testing of these expert systems. Uncertainty in reservoir properties is taken into account by varying the reservoir parameters within an estimated range of values. Analysis of results obtained from trained networks showed error values of less than 3% for prediction of gas and water production profiles (forward networks), while those that are obtained for prediction of reservoir characteristics gave error levels of 15-18% (inverse networks). Forward networks were then used for optimization of field development based upon the criteria of maximizing the net present value (NPV) of a given field. Several case studies were carried out and analyzed.