Estimation of carbon and nitrogen contents in citrus canopy by low-altitude remote sensing

The study aimed to investigate the fast and nondestructive method for detecting carbon and nitrogen content in citrus canopy. The multispectral imagery of Tarocco blood orange (Citrus sinensis L. Osbeck) plant canopy was obtained by a multispectral camera array mounted at an eight-rotor unmanned aerial vehicle (UAV) flying at an altitude of 100 m above the canopy in Wanzhou District of Chongqing Municipality, China. Average spectral reflectance data of the whole canopy, mature leaf areas and young leaves areas were extracted from the imagery. Two spectral pre-processing methods, multiplicative scatter correction (MSC) and standard normal variable (SNV), and two modeling methods, the partial least squares (PLS) and the least squares support vector machine (LS-SVM), were adopted and compared for their prediction accuracy of total content of nitrogen, soluble sugar and starch in the leaves. The results showed that, based on the spectral data extracted from the mature leaves in the multispectral imagery, the PLS model based on the original spectrum obtained a R^sub p^ (correlation coefficient) of 0.6469 and RMSEP (root mean squares error of prediction ) of 0.1296, suggested that it was the best for the prediction of total nitrogen content; the PLS model based on MSC (multiplicative scatter correction) spectrum pre-processing was the best for predicting total soluble sugar content (R^sub p^=0.6398 and RMSEP=8.8891); and the LS-SVM model based on MSC was the best for the starch content prediction (R^sub p^=0.6822 and RMSEP=14.9303). The prediction accuracy for carbon and nitrogen contents based on the spectral data extracted from the whole canopy and the young leaves were lower than that from the mature leaves. The results indicate that it is feasible to estimate the carbon and nitrogen contents by low-altitude airborne multispectral images.