Discrimination of pistachio cultivars based on multi-elemental fingerprinting by pattern recognition methods

The potential of multi-elemental fingerprinting based on inductively coupled plasma optical emission measurements (ICP OES) was examined to classify pistachio cultivars. Five cultivar samples were collected during the harvesting period 2017–2018 from Kerman in Iran. ability multivariate data analysis approaches, such as principal component (PCA) and analysis-linear discriminant (PCA-LDA) have been investigated order achieve discrimination different Eighteen variables i.e. contents Al, B, Ba, Ca, Cd, Co, Cr, Cu, Fe, K, Li, Mg, Mn, Na, Ni, Pb, Sr Zn at mg g?1 level, determined by ICP OES used. results showed that five cultivars can be identified fingerprints. loading plot PCA illustrated Ba lowest contributions Almost all correctly classified PCA-LDA model using cross validation (99.0%). mean sensitivity specificity 98.0% 99.6%, respectively, indicating satisfactory performance model. demonstrate combined with methods employed an effective feasible method for classification Iranian their