Large-scale wheat lodging monitoring by band transformation of UAV and sentinel-2A multispectral imagery

• Wheat lodging monitoring achieved through integration of UAV and Sentinel-2A imagery. • Band transformation between UAV and satellite data enhanced using Multilayer Perceptron. • Wheat lodging ratios estimated with precision by the SPA_XGBoost model. Lodging negatively affects wheat yield and quality. Large-scale remote sensing monitoring of wheat lodging is significant for rapidly assessing the impacts of agricultural disasters and formulating precise management strategies. Large-scale remote sensing of wheat lodging requires sufficient in-situ samples, which are faced with the challenges of high cost, low efficiency, and poor real-time performance. This study proposes a method integrating unmanned aerial vehicle (UAV) and satellite (Sentinel-2A) multispectral imagery to achieve low-cost and efficient wheat lodging monitoring. By applying a multilayer perceptron (MLP) algorithm for band transformation, a wheat lodging ratio (WLR) estimation model was constructed based on high-precision UAV data and migrated to satellite data. This model was used to map the distribution of wheat lodging in Henan Province, China. The MLP algorithm achieved high accuracy and stability in band transformation between UAV and Sentinel-2A imagery, with R 2 values > 0.97 and RMSE values < 0.015. The SPA_XGBoost model delivered the optimal performance in UAV-based WLR monitoring, with a testing set R 2 of 0.8675, RMSE of 0.0732, and NRMSE of 12.13 %. When applied to satellite imagery for WLR monitoring, the model yielded validation accuracies of R 2 = 0.8458, RMSE = 0.0985, and NRMSE = 11.24 %. In addition, UAV imagery was used to generate high-accuracy reference data, thereby laying a robust foundation for model construction and transfer. This study significantly reduced the time and economic costs of acquiring ground-truth samples and offered an effective solution for large-scale remote sensing of crop lodging that balances accuracy and scale.