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

Abstract

To develop a stable estimation model and identify effective wavelengths that could explain the variations in leaf nitrogen (N) concentration with different N supplies, 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 (visible and near-infrared region). On the basis of the canopy raw spectral reflectance data and their subsequent transformation by two different techniques, firstderivative reflectance (FDR) and continuum removal (CR), four multivariate regression methods were comparatively analyzed 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 N 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 centered at 508, 525, 572, 709, 780, 876, and 925 nm were specified using the FDR technique. Based on the full wavelengths, the FDR-SVM model exhibited a good performance for leaf N concentration estimation, with coefficients of determination (r 2 val) for the validation datasets and corresponding relative percent deviations (RPD val) values of 0.842 and 2.383, respectively. However, the FDR-PLS yielded a more accurate assessment of the leaf N concentration than did the other methods, with r 2 val and RPD val 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 centered at 525, 573, 710, 780, 875, and 924 nm were identified for leaf N concentration estimation. The SVM regression method with the effective wavelengths

Monitoring Leaf Nitrogen Accumulation With Optimized Spectral Index in Winter Wheat Under Different Irrigation Regimes

“…Therefore, it contains the information of interest and the information of interference. The application of proper spectral preprocessing can generate good prediction accuracy (Li L. et al, 2016;Li et al, 2020). In this study, the spectra processed with three transformation methods had improved the correlation coefficient with LNA (Figure 4), and the transformed-based spectral index had better performance in LNA estimation (Table 4).…”

High frequency UV–Vis sensors estimate error in riverine dissolved organic carbon load estimates from grab sampling

“…21 components were selected from 248 wavelengths following initial analysis and prior to cross validation steps. Following cross validation, seven components were selected with variable importance in projection scores > 1 (Li et al, 2020 ). This chosen number of components provided a strong degree of explanatory power without overfitting the model, achieving a cross validation correlation of 0.55.…”

Selection of Hyperspectral Vegetation Indices for Monitoring Yield and Physiological Response in Sweet Maize under Different Water and Nitrogen Availability

“…Water and nitrogen (N) represent two major limiting factors for maize production [1]. Water stress acts directly on growth and development, photosynthesis, dry mass production; in addition yield [2] might be severely diminished, especially if water deficiency is prolonged [3].…”

“…Water stress acts directly on growth and development, photosynthesis, dry mass production; in addition yield [2] might be severely diminished, especially if water deficiency is prolonged [3]. Nitrogen is considered the most crucial nutrient for proper growth and development, as it is the principal regulator of many physiological and biochemical processes, and is strongly linked to chlorophyll content [4][5][6] and quantity of yield [1]. Matching N supply to water availability, both spatially and temporally, is essential to accomplish optimal crop response, offering opportunities for precision agriculture [7].…”

“…Field spectroradiometers can generate a continuous spectrum for any object [1] because of their ability to collect spectral signatures in narrow (<10 nm) and contiguous wavelengths in the visible and near-infrared region; thus, they represent effective tools to estimate crop status [21], as well as morpho-physiological [22] and biochemical plant traits at different phenological stages [23].…”