Determination and modeling of multi-element markers for the geographical origin of sweet oranges from Argentina

Abstract

Sweet oranges stand out as one of the most popular fruits in the market, mainly due to their broad consumer appeal. These citrus fruits are valued for their high nutraceutical value and constitute a rich natural source of various nutrients and bioactive compounds. Ensuring the authenticity of these fruits is essential to maintain consumer confidence, promote transparency in sourcing, and protect the reputation of producers in the marketplace. In this study, we investigated the feasibility of using multi-element profiles combined with pattern recognition algorithms to trace the origin of sweet orange samples. To achieve this goal, an optimized microwave plasma atomic emission spectroscopy (MP-AES) method was used to analyze the elemental composition (Al, Ba, Ca, Cd, Co, Cr, Cu, Fe, K, Li, Mg, Mn, Mo, Na, Ni, Pb, Sr, and Zn) of 183 orange samples from four production regions in northeastern Argentina. Exploratory analysis using principal component analysis (PCA) revealed pattern trends among the geographic similarities of the samples. Using the region of origin as a classification factor, support vector machine (SVM), random forest (RF), and gradient boosting tree (GBT) models were then built using the collected data to find elemental tracers of origin identity. The GBT model showed the best classification performance, achieving a 96.5% correct prediction rate on test samples, as confirmed by the ROC curve (AUC=0.973). This approach provides compelling evidence for the potential utility of MP-AES in combination with supervised modeling to determine the geographic origin of sweet orange fruit, thus helping to protect consumers from financial fraud.