PSO-BP Neural Network Model for Predicting Water Temperature in the Middle of the Yangtze River

River temperature prediction is an important project in the environmental impact assessments. Based on river temperature data of Yichang hydrological station in the middle reach of the Yangtze River, BP neural network model based on particle swarm optimization (PSO) was applied to predict river temperature of the Yangtze River. PSO was used to optimize the initial weights of nodes in BP neural network and overcome the over-fitting problem and the local minima problem of the BP neural network. MATLAB was applied to simulate the model. The results show that the prediction precision was improved greatly and the model had better generalization performance. The study proved that PSO-BP neural network model was effective in river temperature prediction.