Classification of Montepulciano d'Abruzzo wines by linear discriminant analysis and artificial neural networks

The data relative to the chemical composition of Montepulciano d'Abruzzo wi nes were elaborated by an Artificial Neural Networks -ANN- analysis procedu re. The same data were also elaborated by a multivariate analysis procedure (Linear Discriminant Analysis -LDA-). These procedures were used in an att empt to classify/characterize the wines. The data came from the chemical an alysis of 116 wine samples produced during two years in three zones of Mont epulciano d'Abruzzo hypothesized to be different pedoclimatically. Classifi cation of the samples according to the year of production only, as well as according to the pedoclimatic zone only, was attempted. The results show th at the analysis allows information to be obtained which is particularly use ful for characterizing the wines according to the year of production.