An adaptive neuro fuzzy inference system was used for classifying water quality status of river.It applied several physical and inorganic chemical indicators including dissolved oxygen,chemical oxygen demand,and ammonia-nitrogen.A data set (nine weeks,total 845 observations) was collected from 100 monitoring stations in all major fiver basins in China and used for training and validating the model.Up to 89.59% of the data could be correctly classified using this model.Such performance was more competitive when compared with artificial neural networks.It is applicable in evaluation and classification of water quality status.