Key points are not available for this paper at this time.
Global agricultural monitoring systems face unprecedented challenges due to intensifying climate change. This paper reviews the advancements in existing global agricultural monitoring systems, highlighting deficiencies in addressing extreme weather events, data integration, and real-time analysis. To overcome these limitations, we introduce the Earth System Model-Coupled Global Agricultural Monitoring System (ESM-GAMS), an advanced framework that combines satellite and near-surface remote sensing, artificial intelligence-driven modeling, supercomputing, and crop model to enhance the accuracy and timeliness of crop monitoring and yield predictions under diverse climate scenarios. By integrating multi-source remote sensing data, ESM-GAMS mitigates delays caused by satellite revisit cycles and weather interference, enabling near real-time monitoring with results available at hourly or minute-level intervals. Additionally, the system demonstrated high accuracy in yield simulations under extreme weather, with the improved WOFOST model achieving robust R 2 values ranging from 0.55 to 0.77, indicating its reliability in predicting yields across diverse conditions. ESM-GAMS not only enables detailed daily monitoring of crop growth, but also provides early-warning capabilities for extreme weather and its impact on prediction. By optimizing resource allocation, supporting climate resilience, and enabling global data computing, ESM-GAMS represents a further step toward achieving climate-smart agriculture. • ESM-GAMS is developed for global agricultural monitoring coupled with Earth System Model. • Integrate satellite and ground data for near real-time agricultural monitoring. • Enhance extreme weather monitoring and prediction using AI and coupler. • Improve yield prediction under extreme weather using WOFOST crop model.
Yu et al. (Thu,) studied this question.