Clasification of drinking water samples using the Chernoff's Faces visualization approach

Our study shows the importance of drinking water monitoring using simple but powerful visualization tools to better understand spatial variations in water quality. The paper reports Chemoff's Faces visualization approach applied for the classification of drinking water samples collected at twelve various districts of Gdansk (Poland), over the period 1993-2000. A good visualization should give the viewer a rapid understanding of the data and the phenomenon behind the data. The complex data matrix containig 1756 results of determination of disinfection by-products (THMs: CHCl3, CHBrCl2 +C-2 HCl, CHBr2Cl, CHBr3, and organolialogen compounds: CCl4, CH2Cl2,C2CI4C2H3Cl3) was successfully treated with Chernoff's approach, yielding two different groups of similarity among the sampling sites, and reflecting different types of drinking water supplies (surface and groundwater).