Near-infrared spectroscopy and machine learning to detect olive oil type: a systematic review

Abstract

The present study evaluates the effectiveness of visible/near-infrared spectroscopy (VIS/NIR) combined with machine learning in olive oil type detection. A search strategy based on the population, intervention, comparison, and outcome (PICO) framework was employed to formulate specific equations used in Scopus, ScienceDirect, and PubMed databases. After applying exclusion criteria, 53 studies were included in the review following preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The reviewed studies demonstrate that VIS/NIR spectroscopy coupled with machine learning allows rapid and accurate identification of different types of olive oil, highlighting the detection of fatty acids, polyphenols, and other vital compounds. However, variability in samples and processing conditions present significant challenges. Although the results are promising, further research is required to fully validate the efficacy and feasibility of this technology in industrial settings. This review provides a comprehensive overview of the advances, challenges, and opportunities in this field, highlighting the need to optimize machine learning models and standardize analysis procedures for practical application in the food industry.