Estimation of Leaf Nitrogen Content in Wheat Using New Hyperspectral Indices and a Random Forest Regression Algorithm

Abstract

Novel hyperspectral indices, which are the first derivative normalized difference nitrogen index (FD-NDNI) and the first derivative ratio nitrogen vegetation index (FD-SRNI), were developed to estimate the leaf nitrogen content (LNC) of wheat. The field stress experiments were conducted with different nitrogen and water application rates across the growing season of wheat and 190 measurements were collected on canopy spectra and LNC under various treatments. The inversion models were constructed based on the dataset to evaluate the ability of various spectral indices to estimate LNC. A comparative analysis showed that the model accuracies of FD-NDNI and FD-SRNI were higher than those of other commonly used hyperspectral indices including mNDVI705, mSR, and NDVI705, which was indicated by higher R2 and lower root mean square error (RMSE) values. The least squares support vector regression (LS-SVR) and random forest regression (RFR) algorithms were then used to optimize the models constructed by FD-NDNI and FD-SRNI. The p-R2 values of the FD-NDNI_RFR and FD-SRNI_RFR models reached 0.874 and 0.872, respectively, which were higher than those of the exponential and SVR model and indicated that the RFR model was accurate. Using the RFR inversion model, remote sensing mapping for the Operative Modular Imaging Spectrometer (OMIS) image was accomplished. The remote sensing mapping of the OMIS image yielded an accuracy of R2 = 0.721 and RMSE = 0.540 for FD-NDNI and R2 = 0.720 and RMSE = 0.495 for FD-SRNI, which indicates that the similarity between the inversion value and the measured value was high. The results show that the new hyperspectral indices, i.e., FD-NDNI and FD-SRNI, are the optimal hyperspectral indices for estimating LNC and that the RFR algorithm is the preferred modeling method.

Determination of Leaf Nitrogen Concentrations Using Electrical Impedance Spectroscopy in Multiple Crops

“…A maximum correlation coefficient of 0.94 is obtained with a minimum RMSE of 1.12%, using EIS measurements for 111 observations, whereas, for the same observations and using SPAD, a maximum correlation coefficient of 0.72 is obtained, and the RMSE is 1.52%. Overall, satisfactory results are presented in this work in comparison with previously published works on optical spectroscopy [4], [7], and on electrical impedance spectroscopy [21,22]. A strong correlation was found between nitrogen concentrations and impedances of the crop leaves measured by EIS with multiple features, and the nitrogen concentrations of the leaves were also determined accurately with the best multiple regression results.…”

“…The proposed multiple linear regression models based on EIS measurements sensitive to LNC can be used on a very local scale to develop a simple, rapid, inexpensive, and effective instrument for determining the leaf nitrogen concentrations in crops.Remote Sens. 2020, 12, 566 2 of 18 and hyperspectral imaging are mostly desirable as rapid, nondestructive, and noninvasive methods for predicting nitrogen in the leaves [4][5][6]. Leaf chlorophyll content is a key indicator of plant physiological status.…”

“…It is correlated with leaf nitrogen concentration, although the correlation depends on soil condition, plant species, and the stage of growth [7][8][9][10][11][12]. The nitrogen status in the leaves can also be determined by analyzing the distribution of the color components of an image of a single leaf or group of plants.In one study, leaf nitrogen status was determined by hyperspectral indices which were based on various algorithms [4]. In other studies, hyperspectral remote sensing images and spectral indices were used to assess the leaf nitrogen status and reflectance spectra of a wheat and reed canopy, as shown by the variation in wavelengths [13][14][15].…”

“…Remote Sens. 2020, 12, 566 2 of 18 and hyperspectral imaging are mostly desirable as rapid, nondestructive, and noninvasive methods for predicting nitrogen in the leaves [4][5][6]. Leaf chlorophyll content is a key indicator of plant physiological status.…”

“…In one study, leaf nitrogen status was determined by hyperspectral indices which were based on various algorithms [4]. In other studies, hyperspectral remote sensing images and spectral indices were used to assess the leaf nitrogen status and reflectance spectra of a wheat and reed canopy, as shown by the variation in wavelengths [13][14][15].…”