It is difficult to predict water quality in a reservoir because of the complex physical, chemical, and biological processes involved. In contrast to the well-known numeric models and artificial neural network models, Linguistic Models (LM) with context-based fuzzy clustering can offer reliable predictions of water quality. The main characteristics of LM are that it is user-centric and that it inherently dwells upon collections of highly interpretable and user-oriented entities, such as information granules. In this paper, we propose a model for evaluating water quality and then evaluate the effectiveness of the proposed method by performing comparisons on water quality data sets from a reservoir. Finally, we found that the proposed method not only has the better prediction performance than other models, but also can offer reliable intervals for uncertainty evaluation about the water quality.