rivers and runoff have always been of interest to human beings. in order to make use of the proper water resources, human societies, industrial and agricultural centers, etc. have usually been established near rivers. as the time goes on, these societies developed, and therefore water resources were extracted more and more. consequently, conditions of water quality of the rivers experienced rapid changes. to face this problem, quality management of the rivers became inevitable. the first and the foremost phase of the quality management is zonation of water quality, because it provides the researcher with proper understanding of the processes and how’s of pollution changes with regard to specific temporal and special conditions. the present research was designed to study the zonation of pollution quality of water in siminieh rood river using artificial neural networks (ann). qualitative data used in this study was collected by sampling in three seasons of spring and fall1387 and spring 1388. the data was then simulated making use of qual2k model. the output was then compared with actual data and parameters nitrate, dissolved oxygen, and electrical conductivity related to fall 1387 were utilized target data in neural network models. data related to land users, geology, erosion capability, and population centers related to simineh rood basin was introduced to neural network models as input data. in the present study, five models of neural networks were used, which finally, ffbp model was known to have maximum estimation precision and qualitative parameters prediction. the result of this model was compared with the output resulted from multivariable regression model, which resulted in proving superiority of the cited neural network model.