摘要

Chemometric methods are powerful in finding hidden structures and latent information in environmental and other analytical datasets. This work shows the application of cluster analysis, discriminant analysis, and support vector machines for the evaluation of waterbodies in the Polish Tatra Mountains. After the analysis of in situ parameters and the determination of concentrations of cations and anions, cluster analysis shows that the previous separation into Western Tatras and High Tatras should be reconsidered, as the Bystra stream in the border region might have been incorrectly assigned to the Western Tatras up to now. Discriminant analysis not only confirms the geographical separation of waterbodies, but also the fact that the sampling time is a crucial factor in environmental analysis. Samples taken in different months do not result in a homogenous object of investigation. A uniform date should therefore be chosen so that the results will be comparable. The influence of the sampling month on the classification of samples is also approved by support vector machines.

  • 出版日期2011-1

全文