抄録
Optimizing crop rotation through data-driven approaches has emerged as a promising strategy for improving soil structure, enhancing soil fertility, and promoting sustainable agricultural production. This review systematically synthesizes recent advances in the application of big data to crop rotation optimization, with emphasis on multi-source data integration, soil property modeling, intelligent rotation planning, yield prediction, and decision-support systems. Recent studies demonstrate that the integration of remote sensing, sensor networks, machine learning, and spatial analysis enables dynamic assessment of soil conditions, improves rotation design under heterogeneous environments, and enhances resource-use efficiency and agroecosystem sustainability. The review further examines key challenges, including data heterogeneity, limited model transferability, interoperability of heterogeneous datasets, and data governance, and discusses emerging opportunities arising from artificial intelligence, digital twins, and cross-regional agricultural data platforms. By integrating advances in big data analytics with crop rotation management, this review establishes a comprehensive framework for data-driven rotation optimization and identifies future research priorities for intelligent soil management and sustainable agricultural intensification.
