A strategic planning model for urban transportation analysis is presented. This model is based on the incorporation and representation of the land use-transportation system interaction under a spatial-temporal approach to forecast travel demand within urban areas. This conception becomes possible due to the integration of Neural Networks (NN), Geographical Information Systems (GIS) and Remote Sensing (RS). A case study in Boston Metropolitan Area was conducted to verify the efficiency of the model and evaluate the best NN structure and also changes in the hidden and output layers were simulated. A recognition rate of 94% was reached expressing the successful definition of the NN. It does mean that the integration of techniques used in this model is appropriated.