Abstract:

To realize the rapid inversion of leaf nitrogen content (LNC) in the canopy of field potatoes, the spectral data of potato canopy leaves were obtained by an imaging spectrometer of a low-altitude unmanned aerial vehicle (UAV) platform. Based on the comprehensive comparison of original reflectance (R), reciprocal transformation reflectance (1/R), first-order differential transformation reflectance [D(R)], second-order differential transformation reflectance [D(2R)], and logarithm of reciprocal transformation reflectance [lg(1/R)], [D(2R)] was selected for the subsequent experiment. Correlation analysis (CA), competitive adaptive reweighed sampling (CARS) and uninformative variables elimination (UVE) algorithms were introduced to screen the characteristic spectral bands, and partial least squares regression (PLSR) and support vector machine (SVM) algorithms were used to construct the LNC estimation model. It was shown that 26, 12 and 19 characteristic bands were screened out by CA, CARS and UVE algorithms, respectively. Among all the established PLSR models, the one based on characteristic bands sreend out by UVE [UVE-D(2R)-PLSR for short] had the best performace, as its determinatino coefficient (R²) and root mean square error (RMSE) on the validatin set were 0.806 8 and 0.193 2, respectively. Among all the established SVM models, the one based on characteristic bands screened out by CARS [CARS-D(2R)-SVM for short] had the best performance, as its R² and RMSE on the validation set were 0.831 6 and 0.183 0, respectively. Compared with UVE-D(2R)-PLSR, CARS-D(2R)-SVM showed better modeling effect. The constructed CARS-D(2R)-SVM model was used to estimate LNC based on the spectral image of potato canopy, and the inverse diagram of LNC was plotted, which could help the growers intuitively grasp the potato growth in the field and provide data support for the potato field management.

Key words: unmanned aerial vehicles, hyperspectrum, potato, support vector machine, inversion