Artificial neural network modeling of water quality of the Yangtze River system: a case study in reaches crossing the city of Chongqing

An effective approach for describing complicated water quality processes is very important for river water quality management. We built two artificial neural network （ANN） models, a feed-forward back-propagation （BP） model and a radial basis function （RBF） model, to simulate the water quality of the Yangtze and Jialing Rivers in reaches crossing the city of Chongqing, P. R. China. Our models used the historical monitoring data of biological oxygen demand, dissolved oxygen, ammonia, oil and volatile phenolic compounds. Comparison with the one-dimensional traditional water quality model suggest that both BP and RBF models are superior; their higher accuracy and better goodness-of-fit indicate that the ANN calculation of water quality agrees better with measurement. It is demonstrated that ANN modeling can be a tool for estimating the water quality of the Yangtze River. Of the two ANN models, the RBF model calculates with a smaller mean error, but a larger root mean square error. More effort to identify out the causes of these differences would help optimize the structures of neural network water-quality models.