Artificial neural network modeling of water quality of the Yangtze River system: a case study in reaches crossing the city of Chongqing |
| |
Authors: | GUO Jin-song and LI Zhe |
| |
Institution: | Faculty of Urban Construction and Environmental Engineering, Chongqing University, Chongqing 400030, P.R. China |
| |
Abstract: | An effective approach for describing complicated water quality processes is very important for fiver 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 su'uctures of neural network water-quality models. |
| |
Keywords: | water quality modeling Yangtze River artificial neural network back-propagation model radial basis function model |
本文献已被 CNKI 维普 万方数据 等数据库收录! |
| 点击此处可从《重庆大学学报(英文版)》浏览原始摘要信息 |
| 点击此处可从《重庆大学学报(英文版)》下载免费的PDF全文 |