Agricultural supply chains are crucial to ensuring that the world’s food demand is met effectively but also sustainably. This paper focuses on the Supply Chain Management (SCM) in agriculture with particular reference to perishable commodities such as tomatoes. The characteristics of tomatoes such as their short shelf life, vulnerability to environmental factors and poor stakeholder networks present a major challenge to production, post-harvest handling, transportation, and market distribution. The advent of Artificial Intelligence (AI) and Machine Learning (ML) have emerged as promising tools to address these challenges through data-driven decision-making, automation, and predictive analytics. A total of 116 studies were referred and synthesized based on a multi-stage title, abstract, and full-text selection process, which used Web of Science, Scopus, IEEE Xplore, and ScienceDirect, combining qualitative thematic evaluation with quantitative bibliometric analysis. The review synthesizes AI/ML applications across agricultural SCM and key stages of the tomato supply chain, including smart farming, post-harvest quality assessment, cold-chain logistics, distribution, and consumer-level traceability. AI/ML methods can optimize operations like smart farming, post-harvest quality assessment, logistics optimization, and market forecasting. These applications contribute to sustainability by reducing food waste, improving resource efficiency, lowering emissions, and enhancing farmer livelihoods. With the focus of sustainability, this study provides insights for advance tomato supply chains using AI-driven technologies.
Wagle et al. (Sun,) studied this question.