AI-driven innovations in postharvest management: Applications, challenges, and future directions

Abstract Postharvest losses account for approximately 30–40% of global agricultural produce, posing a significant threat to food security and economic sustainability. Managing these losses efficiently requires innovative technologies that enhance precision, monitoring, and decision-making across the value chain. Artificial intelligence (AI) has emerged as a transformative tool with applications in postharvest handling utilizing machine learning, computer vision, robotics, and the Internet of Things. This review offers an in-depth analysis of AI applications in postharvest processes, encompassing sorting and grading, quality assessment, storage management, packaging, and cold chain logistics. Case studies on grains, fruits, and vegetables illustrate how AI-based models improve produce classification, predict shelf life, detect spoilage, and optimize logistics—minimizing human error and reducing waste. The paper also highlights significant challenges, including limited data quality, high implementation costs, lack of technical expertise, and inadequate infrastructure, especially in the developing nations. Prospects emphasize the need for integrated frameworks combining AI with sustainable technologies, collaborative research, policy interventions, and public–private partnerships to ensure efficient postharvest systems that enhance profitability and strengthen global food security.