Harnessing artificial intelligence and machine learning for fruit quality management: A comprehensive review

Abstract

Plant-derived foods are essential components of the human diet, and their postharvest quality profoundly affects market value, storage stability, and consumer acceptance. Conventional quality evaluation methods relying on manual inspection are often time-consuming, subjective, and inconsistent, creating an urgent need for intelligent, automated alternatives. This review provides a comprehensive synthesis of recent advances in artificial intelligence (AI) and machine learning (ML) for non-destructive fruit quality assessment. Emphasis is placed on imaging-based technologies including RGB, multispectral, hyperspectral, X-ray, and magnetic resonance imaging that enable precise extraction of external and internal quality attributes such as color, texture, geometry, and biochemical composition. The integration of AI with complementary sensing systems, such as electronic noses and tongues, Internet of Things networks, and robotic platforms, is also discussed for achieving real-time sorting, grading, and early disorder detection. Key insights reveal the growing efficacy and versatility of AI-driven solutions in enhancing precision, speed, and sustainability of postharvest management. Nevertheless, challenges remain regarding dataset standardization, model interpretability, and cross-commodity generalization. Future research should focus on explainable AI, multimodal data fusion, and large-scale validation under practical conditions. Collectively, AI-enabled technologies are redefining postharvest fruit quality management toward a more intelligent and sustainable future.