Development of a method for comprehensive water quality forecasting and its application in Miyun reservoir of Beijing, China

Lei Zhang , Zhihong Zou , Wei Shan


Received March 03, 2016,Revised June 22, 2016, Accepted July 09, 2016, Available online October 29, 2016

Volume 29,2017,Pages 240-246

Water quality forecasting is an essential part of water resource management. Spatiotemporal variations of water quality and their inherent constraints make it very complex. This study explored a data-based method for short-term water quality forecasting. Prediction of water quality indicators including dissolved oxygen, chemical oxygen demand by KMnO4 and ammonia nitrogen using support vector machine was taken as inputs of the particle swarm algorithm based optimal wavelet neural network to forecast the whole status index of water quality. Gubeikou monitoring section of Miyun reservoir in Beijing, China was taken as the study case to examine effectiveness of this approach. The experiment results also revealed that the proposed model has advantages of stability and time reduction in comparison with other data-driven models including traditional BP neural network model, wavelet neural network model and Gradient Boosting Decision Tree model. It can be used as an effective approach to perform short-term comprehensive water quality prediction.

Copyright © Research Center for Eco-Environmental Sciences, Chinese Academy of Sciences. Published by Elsevier B.V. and Science Press. All rights reserved.京ICP备05002858号-3