The global gridded crop production dataset at 10 km resolution from 2010 to 2020 (GGCP10) for maize, wheat, rice, and soybean was developed to address limitations of existing datasets characterized by coarse resolution and discontinuous time spans. GGCP10 was generated using a series of adaptively trained data-driven crop production spatial estimation models integrating multiple data sources, including statistical data, gridded production data, agroclimatic indicator data, agronomic indicator data, global land surface satellite products, and ground data. These models were trained based on agroecological zones to accurately estimate crop production in different agricultural regions. The estimates were then calibrated with regional statistics for consistency. Cross-validation results demonstrated the models’ performance. GGCP10’s accuracy and reliability were evaluated using gridded, survey, and statistical data. This dataset reveals spatiotemporal distribution patterns of global crop production and contributes to understanding mechanisms driving changes in crop production. GGCP10 provides crucial data support for research on global food security and sustainable agricultural development.
Read full abstract