Classification of olive cultivars by machine learning based on olive oil chemical composition

• Published in: Food chemistry Vol. 429; p. 136793
• Main Authors: Skiada, Vasiliki, Katsaris, Panagiotis, Kambouris, Manousos E., Gkisakis, Vasileios, Manoussopoulos, Yiannis
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 15.12.2023
• Subjects: algorithms; artificial intelligence; Artificial intelligent models; Authenticity; Chemical composition; coasts; Cultivar classification; cultivar identification; cultivars; extra-virgin olive oil; food chemistry; Greece; Italy; Machine learning; Olive oil; olives; principal component analysis; traceability; Greece; Italy; Authenticity; Cultivar classification; Artificial intelligent models; Chemical composition; Olive oil; Machine learning
• ISSN: 0308-8146; 1873-7072; 1873-7072
• DOI: 10.1016/j.foodchem.2023.136793

•Classification of olive cultivars by machine learning based on olive oil chemical composition.•Olive oil chemical characteristics of Greek and Italian cultivars were studied.•Exploratory data analysis was used to reveal discriminative patterns.•The XGBoost algorithm was used for olive cultivar and geographic classification.•Olive Cultivars and country of origin were predicted with high accuracy. Extra virgin olive oil traceability and authenticity are important quality indicators, and are currently the subject of exhaustive research, for developing methods to secure olive oil origin-related issues. The aim of this study was the development of a classification model capable of olive cultivar identification based on olive oil chemical composition. To achieve our aim, 385 samples of two Greek and three Italian olive cultivars were collected during two successive crop years from different locations in the coastline part of western Greece and southern Italy and analyzed for their chemical characteristics. Principal Component Analysis showed trends of differentiation among olive cultivars within or between the crop years. Artificial intelligence model of the XGBoost machine learning algorithm showed high performance in classifying the five olive cultivars from the pooled samples.