Abstract

Leaf chlorophyll content (LCC) is a key indicator of a plant’s physiological status. Fast and non-destructive monitoring of chlorophyll content in plants through remote sensing is very important for accurate diagnosis and assessment of plant growth. Through the use of laser-induced fluorescence (LIF) technology, this study aims to compare the predictive ability of different single fluorescence characteristic and fluorescence characteristic combinations at various viewing zenith angles (VZAs) combined with multivariate analysis algorithms, such as principal component analysis (PCA) and support vector machine (SVM), for estimating the LCC of plants. The SVM models of LCC estimation were proposed, and fluorescence characteristics—fluorescence peak (FP), fluorescence ratio (FR), PCA, and first-derivative (FD) parameter—and fluorescence characteristic combinations (${\rm FP} + {\rm FR}$, ${\rm FP} + {\rm FD}$, ${\rm FR} + {\rm FD}$, ${\rm FP} + {\rm FR} + {\rm FD}$) were used as input variables for the models. Experimental results demonstrated that the effect of single fluorescence characteristics on the predictive performance of SVM models was: ${\rm FR} \gt {\rm FD} \gt {\rm FP} \gt {\rm PCA}$. Compared with other models, 0° SVM was the optimal model for estimating LCC by higher ${{\rm R}^2}$. The fluorescence spectra and FD spectra observed at 0° and 30° were superior to those observed at 15°, 45°, and 60°. Thus, appropriate VZA must also be considered, as it can improve the accuracy of LCC monitoring. In addition, compared with single fluorescence characteristic, the ${\rm FP} + {\rm FR} + {\rm FD}$ was the optimal combination of fluorescence characteristics to estimate the LCC for the SVM model by higher ${{\rm R}^2}$, indicating better predictive performance. The experimental results show that the combination of LIF technology and multivariate analysis can be effectively used for LCC monitoring and has broad development prospects.

© 2020 Optical Society of America

Effect of fluorescence characteristics and different algorithms on the estimation of leaf nitrogen content based on laser-induced fluorescence lidar in paddy rice

Jian Yang, Jia Sun, Lin Du, Biwu Chen, Zhenbing Zhang, Shuo Shi, and Wei Gong
Opt. Express 25(4) 3743-3755 (2017)

Potential of spectral ratio indices derived from hyperspectral LiDAR and laser-induced chlorophyll fluorescence spectra on estimating rice leaf nitrogen contents

Lin Du, Shuo Shi, Jian Yang, Wei Wang, Jia Sun, Biwu Cheng, Zhenbing Zhang, and Wei Gong
Opt. Express 25(6) 6539-6549 (2017)

Estimating the leaf nitrogen content of paddy rice by using the combined reflectance and laser-induced fluorescence spectra

Jian Yang, Lin Du, Jia Sun, Zhenbing Zhang, Biwu Chen, Shuo Shi, Wei Gong, and Shalei Song
Opt. Express 24(17) 19354-19365 (2016)

Assessing different regression algorithms for paddy rice leaf nitrogen concentration estimations from the first-derivative fluorescence spectrum

Jian Yang, Lin Du, Yinjia Cheng, Shuo Shi, Chengzhi Xiang, Jia Sun, and Biwu Chen
Opt. Express 28(13) 18728-18741 (2020)

Selection of the optimal bands of first-derivative fluorescence characteristics for leaf nitrogen concentration estimation

Jian Yang, Yinjia Cheng, Lin Du, Wei Gong, Shuo Shi, Jia Sun, and Biwu Chen
Appl. Opt. 58(21) 5720-5727 (2019)