The water quality has deteriorated rapidly in river of Taiwan in the past decades as a result of urbanization, industrialization and population growth over the river basin. Moreover, Taiwan endures contrasting seasonal variations in river flow and water quality because of the short duration and severe intensity of storms and typhoons that attack Taiwan. Sudden changes in river flow caused by extreme climatic events may impose serious degradation on river water quality and huge impacts on ecosystems. This study attempts to identify the crucial water quality variable that significantly correlated with the other water quality parameters affecting river water quality through correlation analyses and further establish a concentration estimation model for this crucial variable by artificial neural networks coupled with a factor analysis. The results provide useful information for reservoir operation managers to sustain acceptable water quality throughout different seasons.