Monitoring of Nitrogen Concentration in Soybean Leaves at Multiple Spatial Vertical Scales Based on Spectral Parameters

Abstract

Nitrogen is a fundamental component for building amino acids and proteins, playing a crucial role in the growth and development of plants. Leaf nitrogen concentration (LNC) serves as a key indicator for assessing plant growth and development. Monitoring LNC provides insights into the absorption and utilization of nitrogen from the soil, offering valuable information for rational nutrient management. This, in turn, contributes to optimizing nutrient supply, enhancing crop yields, and minimizing adverse environmental impacts. Efficient and non-destructive estimation of crop LNC is of paramount importance for on-field crop management. Spectral technology, with its advantages of repeatability and high-throughput observations, provides a feasible method for obtaining LNC data. This study explores the responsiveness of spectral parameters to soybean LNC at different vertical scales, aiming to refine nitrogen management in soybeans. This research collected hyperspectral reflectance data and LNC data from different leaf layers of soybeans. Three types of spectral parameters, nitrogen-sensitive empirical spectral indices, randomly combined dual-band spectral indices, and "three-edge" parameters, were calculated. Four optimal spectral index selection strategies were constructed based on the correlation coefficients between the spectral parameters and LNC for each leaf layer. These strategies included empirical spectral index combinations (Combination 1), randomly combined dual-band spectral index combinations (Combination 2), "three-edge" parameter combinations (Combination 3), and a mixed combination (Combination 4). Subsequently, these four combinations were used as input variables to build LNC estimation models for soybeans at different vertical scales using partial least squares regression (PLSR), random forest (RF), and a backpropagation neural network (BPNN). The results demonstrated that the correlation coefficients between the LNC and spectral parameters reached the highest values in the upper soybean leaves, with most parameters showing significant correlations with the LNC (p < 0.05). Notably, the reciprocal difference index (VI6) exhibited the highest correlation with the upper-layer LNC at 0.732, with a wavelength combination of 841 nm and 842 nm. In constructing the LNC estimation models for soybeans at different leaf layers, the accuracy of the models gradually improved with the increasing height of the soybean plants. The upper layer exhibited the best estimation performance, with a validation set coefficient of determination (R²) that was higher by 9.9% to 16.0% compared to other layers. RF demonstrated the highest accuracy in estimating the upper-layer LNC, with a validation set R2 higher by 6.2% to 8.8% compared to other models. The RMSE was lower by 2.1% to 7.0%, and the MRE was lower by 4.7% to 5.6% compared to other models. Among different input combinations, Combination 4 achieved the highest accuracy, with a validation set R² higher by 2.3% to 13.7%. In conclusion, by employing Combination 4 as the input, the RF model achieved the optimal estimation results for the upper-layer LNC, with a validation set R² of 0.856, RMSE of 0.551, and MRE of 10.405%. The findings of this study provide technical support for remote sensing monitoring of soybean LNCs at different spatial scales.

Keywords: hyperspectral; leaf nitrogen content; remote sensing; soybean; spectral parameters.

Figure 1

Study area.

Figure 2

Leaf sampling details of each layer of the soybean plant.

Figure 3

Statistics of the LNC in each leaf layer of soybean. The horizontal line in the box line diagram represents the median, and the white box represents the average value. The N_RL modeling set is dark brown and the validation set is light brown. The N_LL modeling set is dark purple and the validation set is light purple. The N_CL modeling set is dark blue and the validation set is light blue.

Figure 4

The correlation matrix diagrams of the spectral indices and soybean LNCs. (a1) RI and N_CL; (a2) RI and N_LL; (a3) RI and N_RL; (b1) DI and N_CL; (b2) DI and N_LL; (b3) DI and N_RL; (c1) SAVI and N_CL; (c2) SAVI and N_LL; (c3) SAVI and N_RL; (d1) NDVI and N_CL; (d2) NDVI and N_LL; (d3) NDVI and N_RL; (e1) TVI and N_CL; (e2) TVI and N_LL; (e3) TVI and N_RL; (f1) mSR and N_CL; (f2) mSR and N_LL; (f3) mSR and N_RL; (g1) mNDI and N_CL; (g2) mNDI and N_LL; (g3) mNDI and N_RL; (h1) PI and LNC_CL; (h2) PI and LNC_LL; (h3) PI and LNC_RL; (i1) SI and LNC_CL; (i2) SI and LNC_LL; (i3) SI and LNC_RL; (j1) VI6 and LNC_CL; (j2) VI6 and LNC_LL; and (j3) VI6 and LNC_RL. The colors from blue to red represent the negative correlation to positive correlation.

Figure 5

The modeling set and validation sets of the BPNN estimation models with different input variables and leaf layers. The red dots and red lines represent the modeling sets and the modeling set fitted curves, the blue dots and blue lines represent the verification sets and the verification sets fitted curve, and the dotted lines represent the 1:1 lines.

Figure 6

The modeling sets and validation sets of the PLSR estimation models with different input variables and leaf layers. The red dots and red lines represent the modeling sets and the modeling set fitted curves, the blue dots and blue lines represent the verification sets and the verification set fitted curves, and the dotted lines represent the 1:1 lines.

Figure 7

The modeling sets and validation sets of RF estimation models with different input variables and leaf layers. The red dots and red lines represent the modeling sets and the modeling set fitted curves, the blue dots and blue lines represent the verification sets and the verification set fitted curves, and the dotted lines represent the 1:1 lines.