Leaf chlorophyll content (LCC) is directly related to crop photosynthetic efficiency and is commonly used to evaluate crop health and potential yield. For wheat, a major global food source, accurate LCC data during the growing season is essential for crop health monitoring, nitrogen fertilizer management, and yield prediction. Compared to traditional satellite remote sensing, UAV remote sensing offers the advantages of high spatial resolution and flexibility, making it well-suited for precision agriculture research. However, there is a limited amount of publicly available UAV imagery and synchronized ground observation data for wheat in China, and the standardization is insufficient. This dataset, collected in Gaocheng District, Shijiazhuang City, Hebei Province during the 2024 wheat growing season, includes five UAV multispectral images (taken from March to June), LCC data for 480 wheat plots, Leaf area index (LAI) data for 451 wheat plots, and the corresponding plot location coordinates. Based on ground-truth measurements, a Gaussian process regression model was used to perform LCC inversion for the study area, achieving stable accuracy (RMSE = 5.41μg/cm2, R² =0.90) and a reasonable spatial distribution. The dataset with its large volume and comprehensive coverage of the wheat growing season, along with accurate ground measurements, is valuable for research on wheat LCC and LAI inversion.
Li et al. (Thu,) studied this question.