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

Aug 3, 2026

The study evaluates the effectiveness of visible/near-infrared spectroscopy (VIS/NIR) combined with machine learning for detecting olive oil types. A PICO-based search strategy defined specific queries for Scopus, ScienceDirect, and PubMed, yielding 53 included studies after exclusions and PRISMA-guided screening. Results indicate rapid and accurate identification of olive oil types by detecting fatty acids, polyphenols, and other key compounds. Challenges include variability in samples and processing conditions, requiring further validation for industrial feasibility.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages13

Reading Time33 min

AccessFree to download

Abstract

Introduction

Importance of olive oil analysis

Spectroscopic identification of chemical compounds

Technical and methodological challenges

Research aim and PICO-based strategy

Near-infrared spectroscopy and machine learning to detect olive oil type: a systematic review Leonardo Ledesma Ortecho, Enrique Romero José, Christian Ovalle, Heli Alejandro Cordova Berona Department of Engineering, Universidad Tecnologica del Perú, Lima, Perú Article history: Received Jul 24, 2024 Revised Mar 20, 2025 Accepted May 23, 2025 Keywords: Olive oil Type of olive oil Visible/near-infrared spectroscopy Machine learning Systematic review Corresponding Author: 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 metaanalyses (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. This is an open access article under the CC BY-SA license. Christian Ovalle Engineering Department Department of Engineering, Universidad Tecnologica del Perú Lima, Perú E-mail: [dovalle@utp.edu.pe](dovalle@utp.edu.pe) Article Info ABSTRACT 1. INTRODUCTION The analysis of olive oil is crucial due to its importance in the food industry and its impact on public health. Thus, visible/near-infrared spectroscopy (VIS/NIR) and machine learning have emerged as promising tools for detecting the type of olive oil. Previous research has extensively explored this area, demonstrating that VIS/NIR spectroscopy combined with machine learning algorithms can offer a rapid, efficient, and non-destructive method to analyze olive oil's chemical and physical characteristics [1]–[4] . However, it is crucial to recognize that these promises are still in the research and development phase. Although studies have shown encouraging results so far, there is still work to be done to fully validate the effectiveness and feasibility of this technology in the real world. Studies have addressed the identification of fatty acids, polyphenols, and other compounds present in olive oil using advanced spectroscopic techniques [5]–[8] . These techniques have the potential to offer a deeper understanding of the chemical composition of olive oil, which could lead to significant improvements in its quality, authenticity, and nutritional value. This would allow the different types of olive oil to be identified. However, despite the possibilities of these techniques, they are still being researched and developed. More studies are needed to validate its effectiveness in various olive oil samples. Furthermore, it is crucial to address technical and methodological challenges, such as standardization of analysis procedures and accurate interpretation of spectroscopic data. The integration of VIS/NIR spectroscopy with machine learning techniques raises fundamental questions, such as its impact on the accuracy of olive oil type detection and its feasibility in industrial environments [9]–[12] . So, more research is needed to answer the following question: How does visible/near-infrared (VIS/NIR) spectroscopy combined with machine learni

FAQs

What combination does the review assess for olive oil type detection?

The review evaluates visible/near-infrared spectroscopy (VIS/NIR) combined with machine learning methods for identifying olive oil types.

How were studies selected in the systematic review?

A PICO-based search strategy was used to build database queries for Scopus, ScienceDirect, and PubMed, followed by exclusion criteria and PRISMA-guided screening, resulting in 53 included studies.

What main challenges limit practical industrial adoption?

Sample variability and differences in processing conditions create significant challenges. The review also emphasizes the need to standardize analysis procedures and optimize machine learning models for industrial settings.

Aug 3, 2026

Upload by Theodora