Machine Learning for Enhanced Sustainability in Food Quality and Safety: A Big Data Classification Perspective

Abstract

This paper explores the pivotal role of machine learning (ML) models and algorithms in classifying and managing big data to enhance food safety and sustainability across the modern food supply chain. The increasing complexity of global food systems and the vast, heterogeneous data generated from various sources necessitate advanced analytical tools beyond traditional methods. This review examines the application of supervised and unsupervised ML techniques, including decision trees, support vector machines, random forests, artificial neural networks, convolutional neural networks, and recurrent neural networks, in critical areas such as contamination detection, hazard classification, predictive maintenance, and quality assurance. Advanced studies highlight the superior performance of ML over conventional methods in domains like aflatoxin detection, food fraud monitoring, and risk prediction in livestock. The integration of Industry 4.0 and 5.0 technologies, such as AI, IoT, blockchain, and cloud/edge computing, is also discussed as a driver for improved efficiency and traceability. Despite the significant progress, the paper addresses key challenges including data imbalance, the scarcity of labeled datasets, the interpretability of complex models, and the integration of these advanced systems with existing regulatory frameworks. By providing a comprehensive overview of current applications and outlining future opportunities and barriers, this paper aims to bridge the gap between research and practical implementation, guiding future innovations in digital food safety management.