抄録
Climate change is intensifying uncertainty in agricultural production, creating an urgent need for da-ta-driven approaches that enhance system resilience and adaptive decision-making. This review systemati-cally synthesizes recent advances in data-driven agriculture by integrating four major technological do-mains: artificial intelligence and machine learning for climate risk prediction and adaptive management, blockchain-enabled resilient agricultural supply chains, remote sensing–Internet of Things fusion for crop monitoring and carbon assessment, and genomics-driven precision breeding for climate adaptation. The review critically examines the principles, applications, and complementary strengths of these technologies, highlighting how multisource data integration, intelligent analytics, and digital connectivity enable more accurate risk assessment, resource optimization, and adaptive crop management under changing climatic conditions. It also identifies key challenges, including data interoperability, model generalization, scalabil-ity, and cross-platform integration, which currently limit large-scale implementation. By establishing an integrated analytical framework linking digital technologies with climate adaptation, this review provides a systematic perspective for advancing climate-resilient, data-driven agricultural systems and accelerating the digital transformation of sustainable agriculture.
