The increase and the complexity of data caused by the uncertain environment is today’s reality. In order to identify water quality effectively and reliably, this paper presents a modified fast clustering algorithm for water quality analysis. The algorithm has adopted a varying weights K-means cluster algorithm to analyze water monitoring data. The varying weights scheme was the best weighting indicator selected by a modified indicator weight self-adjustment algorithm based on K-means, which is named MIWAS-K-means. The new clustering algorithm avoids the margin of the iteration not being calculated in some cases. With the fast clustering analysis, we can identify the quality of water samples. The algorithm is applied in water quality analysis of the Haihe River (China) data obtained by the monitoring network over a period of eight years (2006–2013) with four indicators at seven different sites (2078 samples). Both the theoretical and simulated results demonstrate that the algorithm is efficient and reliable for water quality analysis of the Haihe River. In addition, the algorithm can be applied to more complex data matrices with high dimensionality.

River water is an important source for drinking water supply in Northwestern New Territories of Hong Kong. Thus, there is no denying the fact that monitor the quality of river water is a must for the locals. In this study, a mixed multivariate analysis method was used to lower monitoring costs by optimizing the layout of water quality monitoring stations. To this purpose, the data from a period of five years and over 36,000 observations was evaluated in this article. The cluster analysis approach was also used to categorize monitoring stations into three groups. What's more, three latent factors that predominantly influence the river water quality were assessed using factor analysis: anthropogenic pollution, seawater intrusion and geological processes, and the nitrification process. A spatial pattern using the three latent factor scores was plotted and six redundant monitoring stations were identified by this pattern. Finally, discriminant analysis was used to extract seven significant parameters. The results showed that the surface water-monitoring program of the watercourses in the Northwestern New Territories (Hong Kong) could be adjusted by reducing the monitoring stations to 18 and the measured chemical parameters to seven to ensure the detection of water quality and reduce the cost.