Determination of the principal factors of river water quality through cluster analysis method and its prediction

• Published in: Frontiers of environmental science & engineering Vol. 6; no. 2; pp. 238 - 245
• Main Authors: Guo, Liang, Zhao, Ying, Wang, Peng
• Format: Journal Article
• Language: English
• Published: Heidelberg Springer-Verlag 01.04.2012; Higher Education Press; SP Higher Education Press; Springer Nature B.V
• Subjects: artificial; artificial neural network; Artificial neural networks; Chemical oxygen demand; Cluster analysis; cluster analysis method; clusteranalysis; Earth and Environmental Science; Environment; factor; forecast; Forecasting; Mathematical models; method; network; neural; Neural networks; prediction; Prediction models; principal; principal factor; quality; Research Article; river water; Rivers; surface water; topology; water; Water quality; water quality forecast; water quality forecast; artificial neural network; principal factor; cluster analysis method
• ISSN: 2095-2201; 2095-221X
• DOI: 10.1007/s11783-011-0382-7

In this paper, an artificial neural network model was built to predict the Chemical Oxygen Demand （CODMn） measured by permanganate index in Songhua River. To enhance the prediction accuracy, principal factors were determined through the analysis of the weight relation between influencing factors and forecasting object using cluster analysis method, which optimized the topological structure of the prediction model input items of the artificial neural network. It was shown that application of the principal factors in water quality prediction model can improve its forecasting skill significantly through the comparison between results of prediction by artificial neural network and the measurements of the CODMn. This methodology is also applicable to various water quality prediction targets of other water bodies and it is valuable for theoretical study and practical application.