Yield estimation of winter wheat in the Huang-Huai-Hai region using MODIS and meteorological data: spatio-temporal analysis and county-level modeling

The Huang-Huai-Hai region is a major winter wheat production area in China. Achieving accurate yield estimation through high spatio-temporal resolution MODIS remote sensing combined with meteorological monitoring has become an important issue for ensuring food security. This study integrates multi-source MODIS satellite data (surface reflectance, leaf area index LAI, and fraction of absorbed photosynthetically active radiation FPAR) with precipitation and temperature data to construct a county-level winter wheat yield prediction model. First, spatio-temporal analyses were conducted on multidimensional parameters during key periods (overwintering, growth, and maturation). The results showed that reflectance responded sensitively to phenological changes; FPAR and LAI revealed photosynthetic capacity and canopy structure evolution; monthly mean precipitation and temperature exhibited significant spatio-temporal heterogeneity, providing data support for effective yield prediction. Next, PLS, RF, and BP models were constructed for the three periods. The BP model performed best across multiple periods, achieving the highest accuracy in the growth period (R²=0.81, RMSE=414.48 kg/ha) and was thus selected as the optimal window period and model. Shapley Additive Explanations (SHAP) analysis revealed the influence of model features on yield prediction, with specific reflectance bands, precipitation, and LAI identified as key contributing factors. Furthermore, the BP model was validated using remote sensing and meteorological data from the 2023 growth period, combined with county-level yields. The results showed R²=0.73 and RMSE=509.30 kg/ha, further confirming the model's prediction accuracy and stability in practical applications. This study enables county-level estimation of winter wheat yield, providing scientific evidence and methodological reference for agricultural monitoring and food security assurance.