Abstarct: Nitrogen (N) affects adversely the tobacco yield quantity and quality as it increases yield, chloride and nicotine contents, but decreases potassium content. Nitrate reductase as a key enzyme in the reducing of inorganic nitrogen has a direct impact on plant growth. This experiment was aimed at optimization of (finding the balance between) N concentration in leaf, stem and root and some other traits to increase simultaneously both yield quantity and quality (high potassium, low chloride and medium nicotine contents) using artificial neural network. Two field experiments baxsed on complete block design with three replications were conducted in Tirtash and Urmia tobacco research centers. Treatments were factorial arrangement of two N sources (urea and nitrate ammonium) and four application patterns. The results showed that there were no significant different between two N sources used here (urea and ammonium nitrate). The best application pattern was use of nitrate ammonium in 2/3 basal and urea in 1/3 basal and the rest of them at the beginning of rapid growth stage. It was established two artificial neural networks which their structure were 15-15-4 and 10-12-4. The neural network model showed that the average value of optimized N concentration was 3.06, 2.42 and 1.51% for leaf, stem and root, respectively......