Explainable artificial intelligence techniques for interpretation of food models: a review
Методы объяснимого искусственного интеллекта для интерпретации моделей в пищевой промышленности: обзор
2026-04-24
SCID: 54.1/vkzgjskz
Discuss with AI
Grad-CAMSHAPexplainable artificial intelligencefood engineeringfood quality control
Figures from the paper
Abstract (AI)
Artificial Intelligence (AI) has become essential for analyzing complex data and solving highly-challenging tasks. It is being applied across numerous disciplines beyond computer science, including Food Engineering, where there is a growing demand for accurate and reliable predictions to meet stringent food quality standards. However, this requires increasingly complex AI models, raising concerns. In response, eXplainable AI (XAI) has emerged to provide insights into AI decision-making, aiding model interpretation by developers and users. Nevertheless, XAI remains underutilized in Food Engineering, limiting model reliability. For instance, in food quality control, AI models using spectral imaging can detect contaminants or assess freshness levels, but their opaque decision-making process hinders adoption. XAI techniques such as SHAP (Shapley Additive Explanations) and Grad-CAM (Gradient-weighted Class Activation Mapping) can pinpoint which spectral wavelengths or image regions contribute most to a prediction, enhancing transparency and aiding quality control inspectors in verifying AI-generated assessments. This survey presents a taxonomy for classifying food quality research using XAI techniques, organized by data types and explanation methods, to guide researchers in choosing suitable approaches. We also highlight trends, challenges, and opportunities to encourage the adoption of XAI in Food Engineering.
Key Findings
1
AI is increasingly used in Food Engineering for complex prediction tasks, but model complexity creates interpretability and reliability concerns.
2
SHAP and Grad-CAM can identify influential spectral wavelengths or image regions, helping inspectors verify AI predictions for contamination and freshness detection.
3
The review introduces a taxonomy classifying food-quality studies by data types and explanation methods to support selection of suitable XAI approaches.
4
The survey identifies current trends, challenges, and opportunities for broader XAI adoption in Food Engineering.
5
XAI remains underutilized in Food Engineering, limiting trust and adoption of AI systems for food quality assessment.
Research Object
AI models applied in Food Engineering, particularly for food quality assessment and control
Research Subject
Interpretability and explainability of food-related AI model predictions, including the data features and regions driving quality assessments
Publication Details
Publication Date
2026-04-24
Journal
Publisher
ISSN
Cited by
78
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai8
Greedy function approximation: A gradient boosting machine.2001
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Learning Deep Features for Discriminative Localization2016
Machine Learning in Agriculture: A Comprehensive Updated Review2021
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI2023
Explainable Artificial Intelligence (XAI) 2.0: A manifesto of open challenges and interdisciplinary research directions2024
Application of Artificial Intelligence in Food Industry—a Guideline2021
A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges2025