Non-destructive monitoring of leaf nitrogen (N) status can assist in growth diagnosis, N management and productivity forecast in field crops. The objectives of this study were to determine the relationships of leaf nitrogen concentration on a leaf dry weight basis (LNC) and leaf nitrogen accumulation per unit soil area (LNA) to ground-based canopy reflectance spectra, and to derive regression equations for monitoring N nutrition status in wheat (Triticum aestivum L.). Four field experiments were conducted with different N application rates and wheat cultivars across four growing seasons, and time-course measurements were taken on canopy spectral reflectance, LNC and leaf dry weights under the various treatments. In these studies, LNC and LNA in wheat increased with increasing N fertilization rates. The canopy reflectance differed significantly under varied N rates, and the pattern of response was consistent across the different cultivars and years. Overall, an integrated regression equation of LNC to normalized difference index (NDI) of 1220 and 710 nm of canopy reflectance spectra described the dynamic pattern of change in LNC in wheat. The ratios of several near infrared (NIR) bands to visible light were linearly related to LNA, with the ratio index (RI) of the average reflectance over 760, 810, 870, 950 and 1100 nm to 660 nm having the best index for quantitative estimation of LNA in wheat. When independent data were fit to the derived equations, the average root mean square error (RMSE) values for the predicted LNC and LNA relative to the observed values were no more than 15.1 and 15.2%, respectively, indicating a good fit. Our relationships of leaf N status to spectral indices of canopy reflectance can be potentially used for non-destructive and real-time monitoring of leaf N status in wheat. Key words: Wheat, leaf nitrogen concentration, leaf nitrogen accumulation, canopy reflectance, spectral index, nitrogen monitoring
Leaf Nitrogen Concentration and Plant Height Prediction for Maize Using UAV-Based Multispectral Imagery and Machine Learning Techniques
