Wheat leaf area index inversion using hyperspectral remote sensing technology

The wheat leaf area index (LAI) was inverted using hyperspectral remote sensing technology in the present paper. Eighteen kinds of hyperspectral indices were comparatively analyzed, and the index OSAVI, which could reflect wheat LAI most sensitively, was screened out. The models for wheat LAI inversion were built using the field spectra as the training samples. The study showed that the calibration R-square and prediction R-square of the inversion model which were built by hyperspectral index OSAVI were 0.823 and 0.818, respectively, higher than that of other indices, indicating that the accuracy was highest. The inversion model was spatially quantitatively expressed in OMIS image, and then the inversion value and measured value was compared by the method of regression fitting. The R-square and RMSE of the fitting model were 0.756 and 0.500, respectively, indicating that the similarity between the inversion value and measured value was high. The result showed that it was feasible to invert the wheat LAI by hyperspectral indices, and OSVAI was an optimal one.