The use of spectral features to estimate leaf area index (LAI) is generally considered a challenging task for hyperspectral data. In this study, the hyperspectral reflectance of winter wheat was selected to optimize the selection of spectral features and to evaluate their performance in modeling LAI at various growth stages during 2008 and 2009. We extracted hyperspectral features using different techniques, including reflectance spectra and first derivative spectra, absorption and reflectance position and vegetation indices. In order to find the best subset of features with the best predictive accuracy, partial least squares regression (PLSR) and variable importance in projection (VIP) were applied to estimated LAI values. The results indicated that the red edge–NIR spectral region (680 nm–1300 nm) was the most sensitive to LAI. Most features in this region exhibited a high correlation with LAI and had higher VIP values, especially the first derivative waveband at 750 nm (r = 0.900, VIP = 1.144). Adding a large number of features would not significantly improve the accuracy of the PLSR model. The PLSR model based on the fourteen features with the highest VIP values predicted LAI with a mean bootstrapped R² value of 0.880 and a mean RMSE of 0.943 on the validation dataset and produced an estimated LAI result better than that, including the entire 54-feature dataset with a mean R² of 0.875 and a mean RMSE of 0.965. The results of this study thus suggest that the use of only a few of the best features by VIP values is sufficient for LAI estimation.

Timely assessment of crop N content is critical for crop growth diagnosis and precision management to generate higher yield and better quality. The objective of this study was to determine the optimal spectral index and build a retrieval model for diagnosing shoot N content (SNC) of wheat (Triticum aestivum L.) at vegetative stage using ground‐based hyperspectral reflectance data. Hyperspectral indices were investigated to evaluate their capabilities for wheat N concentration estimation by the Pearson's correlation analysis. The analysis results showed that green normalized difference vegetation index (GNDVI) and the combined spectral index the first derivative of reflectance spectral at 736 nm (D736) × the reflectance at 900 nm (R900)/the reflectance at 720 nm (R720) were most suitable for wheat SNC estimation at vegetative stage. A power model with GNDVI and a linear model with D736 × R900/R720 were appropriate for SNC estimation in vegetative stage. The validation experiments demonstrated that the power model with GNDVI was preferable to the linear mode with D736 × R900/R720 for SNC estimation until the flag leaf stage. However, the linear model with D736 × R900/R720 was better after the flag leaf stage. For wheat SNC assessment at the whole vegetative stage, the linear model with D736 × R900/R720 was the most accurate, of which the root mean square error was 2.391 g m⁻² and the correlation coefficient between the measured and estimated SNC was 0.934 (n = 79).