Securing origin integrity through Machine Learning analysis of Mozzarella di Bufala PDO Microbiome

The origin of food products is an important factor to consider for consumers seeking authentic, high-quality, and safe products. Information about the origin provides valuable guidance for making informed decisions about food purchases and can help promote sustainable agricultural practices. Indeed, machine learning (ML) techniques offer a promising solution for evaluating the geographical origin of food products, including Mozzarella di Bufala Campana PDO. By analyzing various data sources, ML algorithms can discern patterns and associations that correlate with specific geographic regions. For instance, ML models can be trained on datasets containing information about the microbiota composition of Mozzarella di Bufala Campana PDO samples collected from different regions. By leveraging advanced classification or clustering algorithms, these models can learn to differentiate between microbiota profiles associated with distinct geographical origins. The proposed study aimed to implement an explainable artificial intelligence framework using microbiota data from Mozzarella PDO samples from Salerno and Caserta. Our analysis aimed to classify each sample into one of the two origin areas. We employed the XGB classifier, a machine learning algorithm, which achieved an accuracy of 0.825 ± 0.032, a F1-score of 0.849 ± 0.028 and an average AUC of 0.880 ± 0.026. The application of machine learning methods to classify the geographical origin of products, coupled with advanced techniques of chemical and biological analysis supported by artificial intelligence, promises to distinguish between authentic and adulterated products. It is important to ensure that the data used to train the models are representative and reliable. Machine learning could play a vital role in this context by enabling the analysis of vast amounts of data to identify patterns and characteristics unique to specific geographic regions.