River water temperature has been regarded as an important ecological and environmental assessment factor. Interventionof human activities （such as dam construction） often causes abnormal changes in river water temperature and significant effects onriver ecosystem. The effective water temperature prediction can provide a good indication for the long-term evolution trend of theriver thermal dynamics. In this paper， the Air2stream model， which is a newly data-driven water temperature prediction model，has been used in the Yangtze River to explore its temperature variation before and after the operation of Three Gorges Dam. Theperformance of the model is assessed by the root mean square error （RMSE） and the Nash efficiency coefficient （NSE）， with acomparison with other empirical regression models. The results show that the Air2stream model has the advantages of higher accuracyand better stability in the medium and long-term water temperature prediction for the river water temperature that would haveoccurred in absence of the large-scale engineering works or other intensive human interventions. In addition， the difference betweenobserved and simulated values of river water temperature can be used as a useful indicator for assessing the impacts of humaninterventions. The case study applied to the Yangtze River shows that Air2stream can be used to determine the extent of variationof water temperature and main controlled factors， as well as quantitatively analyzes the contributions of both human interventionsand climate change to water temperature mutation. Therefore， it can provide an important technical support for monitoring andmanagement of river ecosystem.