Title :
Water Quality Prediction of Changjiang of Jingdezhen through Particle Swarm Optimization Algorithm
Author :
Xu, Xing ; Hu, Na ; Liu, BingXiang
Author_Institution :
Coll. of Inf. & Eng., Jingdezhen Ceramic Inst., Jingdezhen, China
Abstract :
In order to obtain the water quality trend of Changjiang of Jingdezhen and prevent water pollution events, a water quality prediction model is built. Water quality index data, which are observed from a section of Changjiang, are taken as training samples. And eight indexes are selected, such as PH, chloride, sulfate, dissolved oxygen (DO), ammonia, permanganate, iron, total phosphorus (TP). Radial basis function (RBF) neural network model is optimized by particle swarm optimization (PSO) algorithm, and then the model is used to predict water quality indexes of Changjiang. The experimental results indicate that the deviation of predicted values calculated by the model and observed values are almost less then 4%, and we could infer that RBF neural network model optimized by PSO is a reliable and effective method for water quality prediction.
Keywords :
ammonia; chlorine; environmental science computing; geophysics computing; hydrological techniques; iron; manganese compounds; neural nets; optimisation; oxygen; pH; phosphorus; radial basis function networks; rivers; sulphur compounds; water pollution; water quality; Changjiang; China; Cl-; Fe; Jingdezhen; MnO42-; NH3; O; P; PSO algorithm; RBF neural network model; SO42-; ammonia concentration; chloride concentration; dissolved oxygen concentration; iron concentration; pH; particle swarm optimization algorithm; permanganate concentration; radial basis function; sulfate concentration; total phosphorus concentration; water pollution event prevention; water quality index; water quality prediction model; water quality trend; Indexes; Particle swarm optimization; Predictive models; Radial basis function networks; Rivers; Water pollution; Water resources;
Conference_Titel :
Management and Service Science (MASS), 2011 International Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-6579-8
DOI :
10.1109/ICMSS.2011.5998658