Using discriminant analysis to assess polycyclic aromatic hydrocarbons contamination in Yongding New River

• Published in: Environmental monitoring and assessment Vol. 185; no. 10; pp. 8547 - 8555
• Main Authors: Wang, Xiaojing, Zou, Zhihong, Zou, Hui
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.10.2013; Springer; Springer Nature B.V
• Subjects: Animal, plant and microbial ecology; Applied ecology; Atmospheric Protection/Air Quality Control/Air Pollution; Biological and medical sciences; Carcinogens; Categories; Cluster Analysis; Clustering; Clusters; Conservation, protection and management of environment and wildlife; Datasets; Discriminant Analysis; Earth and Environmental Science; Ecology; Ecotoxicology; Environment; Environmental Management; Environmental monitoring; Environmental Monitoring - methods; Environmental protection; Environmental testing; Freshwater; Fundamental and applied biological sciences. Psychology; Geologic Sediments - chemistry; Monitoring/Environmental Analysis; Pollutants; Polycyclic aromatic hydrocarbons; Polycyclic Aromatic Hydrocarbons - analysis; Population; Principal Component Analysis; Principal components analysis; Random variables; Ratios; Rivers; Rivers - chemistry; Standard deviation; Standard scores; Standardization; Statistical analysis; Studies; Water Pollutants, Chemical - analysis; Water pollution; Water Pollution, Chemical - statistics & numerical data; China; Cluster analysis; Discriminant analysis; Polycyclic aromatic hydrocarbons (PAHs); Standardization; Principal component analysis; Environmental assessment; Hydrocarbon; Rivers; Polycyclic aromatic compound; Mutagen; Contamination; Persistent organic pollutant; Statistical method; Pollution; Environment impact; Stream; Environmental monitoring; Organic compounds
• ISSN: 0167-6369; 1573-2959
• DOI: 10.1007/s10661-013-3194-3

Yongding New River has been polluted by polycyclic aromatic hydrocarbons (PAHs) which are carcinogenic and mutagenic. In three periods (the abundant water period, mean water period, dry water period), ten sites (totally 30 samples) in Yongding New River were clustered into four categories by hierarchical cluster analysis (hierarchical CA). In the same cluster, the samples had the same approximate contamination situation. In order to eliminate the dimensional differences, the data in each sample, containing 16 kinds of PAHs, were standardized with normal standardization and maximum difference standardization. According to the results of the cubic clustering criterion, pseudo F, and pseudo t 2 (PST2), the proper number of clustering for the 30 samples is 4. Before conducting hierarchical CA and K-means cluster analysis on the samples, we used principal component analysis to obtain another group data set. This data set was composed of the principal component scores which are uncorrelated variables. Hierarchical CA and K-means cluster analysis were used to classify the two data sets into four categories. With the classification results of hierarchical CA and K-means cluster analysis, discriminant analysis is applied to determine which method was better for normalization of the original data and which one was proper to cluster the samples and establish discriminant functions so that a new sample can be grouped into the right categories.