Artificial intelligence in food safety and quality control: applications, challenges, and future perspectives

Abstract

The increasing complexity of global supply chains, rising contamination risks, and evolving consumer expectations have made food safety and quality control critical priorities. The limitations of traditional inspection and analytical methods in terms of speed, accuracy, and real-time monitoring have driven the rapid adoption of artificial intelligence (AI)-based technologies in this field. This review evaluates current AI applications in food safety by integrating contaminant detection, hygiene management, quality control, early warning systems, and supply chain traceability into a unified framework while critically examining their advantages, limitations, industrial applicability, and future research priorities. AI-enabled systems support proactive food safety management by improving contaminant detection, whereas the integration of AI with biosensors and smart packaging systems enhances continuous quality monitoring. However, data heterogeneity, high infrastructure costs, limited model interpretability, regulatory challenges, and data privacy concerns remain key barriers to the widespread adoption of AI applications. Overall, AI technologies have the potential to enhance accuracy, proactive management, traceability, and sustainability in food safety. Realizing this potential at an industrial scale requires strengthened interdisciplinary collaboration, standardized data infrastructures, and the development of practical and scalable AI solutions.