Multivariate determination of the geographical origin of wines from four different countries

In the framework of the Wine Database European Project, 400 wine samples from four different countries, namely Hungary, Romania, Czech Republic and South Africa, were collected and 63 chemical parameters were analyzed in order to determine the possibility to identify the origin of a wine from its chemical content. The ability of multivariate analysis methods such as classification and regression trees and partial least squares discriminant analysis and its uninformative variable elimination variant to achieve this classification task is investigated and a special attention is given to variable selection. The results observed show that it is possible to obtain excellent classification rates based on the chemical content of only few parameters, such as for instance the isotopic ratios or the concentration in trace elements. (c) 2006 Elsevier Ltd. All rights reserved.