摘要：Leaf area index (LAI) is one of the most basic parameters to characterize the vegetation canopystructure, and is widely used in monitoring crop growth, yield estimation and other fields. Therefore,accurate estimation of LAI has great significance for agricultural precision fertilization and protectingagricultural ecological environment. However, few studies have attempted to estimate LAI of winterwheat using the continuous wavelet analysis (CWA), particularly at different growth stages. Thispaper aims at studying the spectral estimation of LAI by applying CWA into canopy spectra of 190samples observed at Guanzhong Plain in China. Two partial least square regression (PLSR) modelsusing six wavelet features and the optimal spectral indices were constructed and comparedrespectively. Results indicated that the model using wavelet features combination had a considerableimprovement than the spectral indices combination for the whole validation dataset. When the validationdataset was separated according to the growth stage, the predictive performance of the waveletfeatures combination performed well at both growth stages, while the spectral indices combinationhad not achieved the same effect. The results showed that CWA approach could derive more robustwavelet features to growth stage variation, and wavelet features were more effective than thespectral indices for predicting LAI of winter wheat at different growth stages..
