AUTHOR=Li Lantao , Lin Di , Wang Jin , Yang Liu , Wang Yilun 

TITLE=Multivariate Analysis Models Based on Full Spectra Range and Effective Wavelengths Using Different Transformation Techniques for Rapid Estimation of Leaf Nitrogen Concentration in Winter Wheat

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2020.00755

DOI=10.3389/fpls.2020.00755

ISSN=1664-462X

ABSTRACT=To develop a stable estimation model and identify effective wavelengths that could explain the variations in leaf nitrogen concentration with different N supply, growing seasons, ecological locations, growth stages and wheat cultivars. Four field experiments were performed during two consecutive years (2017-2019) at three sites (Yuanyang, Hebi and Wenxian) in Henan, China. In situ canopy spectral reflectance data under the aforementioned N supply conditions were obtained over a range of 400-950 nm. On the basis of the canopy raw spectral reflectance data and their subsequent transformation techniques, first-derivative reflectance (FDR) and continuum removal (CR), four multivariate regression methods were comparatively analysed and used to develop predictive models for estimating leaf N concentration: multiple linear regression (MLR), principal component regression (PCR) partial least square (PLS) and support vector machine (SVM). Results showed that leaf nitrogen concentration and canopy reflectance significantly varied with the levels of N fertilization, and a good correlation was observed for all the spectral techniques. Seven wavelengths with relatively higher r values than the bands of the raw spectra centred at 508, 525, 572, 709, 780, 876, and 925 nm were specified using FDR technique. Based on the full wavelengths, the FDR-SVM model exhibited a good performance, with coefficients of determination (r2val) for the validation datasets and corresponding relative percent deviations (RPDval) values of 0.842 and 2.383, respectively. However, the FDR-PLS yielded a more accurate assessment of the leaf nitrogen concentration than did the other methods, with r2val and RPDval values of 0.857 and 2.535, respectively. The variable importance in projection (VIP) scores from the FDR-PLS with the all canopy spectral region were used to screen the effective wavelengths of the spectral data. Therefore, six effective wavelengths centred at 525, 573, 710, 780, 875 and 924 nm were identified for leaf nitrogen concentration estimation. The SVM regression method with the effective wavelengths showed excellent performance for leaf nitrogen concentration estimation with r2val= 0.823 and RPDval= 2.280. These results demonstrated that the canopy spectral technique is promising for the estimation of leaf nitrogen concentration in winter wheat based on the FDR-PLS regression model and the effective wavelengths identified.