Multivariate classification and modeling in surface water pollution estimation.

The present study deals with the application of self-organizing maps (SOM) and multiway principal-components analysis to classify, model, and interpret a large monitoring data set for surface water quality. The chemometric methods applied made it possible to reveal specific quality patterns of the chemical and biological parameters used to monitor the water quality (relation between water temperature, turbidity, hardness, colibacteria), seasonal impacts during the long period of observation and the relative independence on the spatial location of the sampling sites (water supply sources for the City of Trieste).