*3.5. MDMV Identification*

The results of the LDA and SVM classification models constructed based on Rλ, VIs, and VIc are shown in Table 3. All models could identify healthy leaves, and the models primarily differed in terms of their identification accuracy of red (i.e., infected) leaves. Both LDA and SVM classification models based on Rλ showed low accuracy, and the number of red leaves identified by the LDA-Rλ model was even lower than zero. Therefore, Rλ is not suitable for the RS-based identification of MDMV-infected leaves. Based on VIs, the SVM model performed better than the LDA model, and the recognition accuracy of the calibration and validation sets exceeded 75% for the former. This is because the SVM algorithm has high classification accuracy and generalizability when the sample size is small, and it performs better in solving classification problems with high-dimensional features [54,55]. In addition, the RBF kernel function used by the SVM algorithm can be adjusted by using a grid search to obtain a better classification model [56,57]. The accuracy of both LDA and SVM classification models based on VIc was 100%, which is significantly higher than that of models based on Rλ and VIs and shows obvious superiority in the RS-based detection of MDMV. This is because the input parameter VIc is constructed based on the spectrum of normal leaf and red leaf at any two bands in the 400–1000 nm region, which has its uniqueness. Moreover, in the VIc contour maps of the red leaves, the most significant areas noted around NDVIh, RVIh, DVIh, and SAVIh were (R573, R507), (R572, R507), (R547, R522), and (R547, R518). In the VIc contour maps of the healthy leaves, the most significant areas around NDVIr, RVIr, DVIr, and SAVIr were (R689, R461), (R460, R692), (R690, R656), and (R685, R667). These bands are located in the wavelength region corresponding to the high SI value, and there is a large difference between the two leaves in this region. In addition, the difference was further enhanced by using difference and ratio calculation to construct the vegetation index, thus achieving the high-precision identification of MDMV-infected and healthy leaves.


**Table 3.** LDA and SVM classification models.

Note: Rλ is the spectral reflectance of red leaves at 695 nm and healthy leaves at 554 nm; VIs is the narrow-band vegetation indices; VIc is the vegetation index constructed based on two arbitrary bands; nr and nh are the number of samples of red and healthy leaves, respectively.

### *3.6. Classic Regression Analysis Based on a Sensitive Band*

In the present study, random stratified sampling was used to divide the dataset at a ratio of 2:1 for obtaining representative samples for calibration and validation. The statistics of the calibration and validation datasets are shown in Figure 8a. The statistics of the calibration and validation datasets were similar for red leaves (max = 0.76 and 0.73; min = 0.05 and 0.04; mean = 0.20 and 0.18; SD = 0.19% and 0.17%; and CV = 96.48% and 95.60%, respectively). For healthy leaves, the maximum values of the calibration and validation datasets were 0.11 and 0.10, respectively, and the remaining statistical parameters were identical between the two datasets. Furthermore, the distribution of calibration and validation data was consistent with that of all data.

**Figure 8.** (**a**) Statistical analysis of calibration set and validation set; (**b**) precision comparison of UR models based on Rλ.

Exponent, linear, exponential, polynomial, and power regression models for Anth were built based on the spectral reflectance of red leaves at 665 nm (R695) and healthy leaves at 554 nm (R554). The R<sup>2</sup> c, R<sup>2</sup> v, RMSEc, and RMSEv for each model are shown in Figure 8b. For the same sample, while the differences in RMSEc and RMSEv were small, R<sup>2</sup> c and R<sup>2</sup> v were significantly different among the various models. Among the models for healthy leaves, the exponential and polynomial models produced reliable results (R<sup>2</sup> c = 0.48, R<sup>2</sup> v = 0.46). Among the models for red leaves, the linear model produced the most reliable results (R<sup>2</sup> c = 0.62, R<sup>2</sup> v = 0.44). The R<sup>2</sup> c and R<sup>2</sup> v values of the univariate

regression (UR) model for Anth based on Rλ were high (*p* < 0.01); however, model accuracy remained low, and it could not accurately estimate the anthocyanin content of leaves.

### *3.7. Anth Regression Models Based on VIs, VIc, and VIs + VIc + R*λ

The Anth estimation models for red and healthy leaves based on VIs, VIc, and VIs + VIc + Rλ and constructed using MLR, PCR, PLSR, and SVMR are shown in Figure 9. The range of R<sup>2</sup> c and R<sup>2</sup> v values of the Anth models for red leaves was 0.63–0.85 and 0.57–0.74, respectively. Among the models based on VIs, the PLSR model (R<sup>2</sup> c = 0.73, R<sup>2</sup> v = 0.61) showed the highest accuracy, followed by the MLR model. Among the VIc-based models, the R<sup>2</sup> c of the MLR, PCA, and PLSR models was equal, and the difference in R<sup>2</sup> v was small. The SVMR model showed the highest accuracy (R<sup>2</sup> c = 0.68, R<sup>2</sup> v = 0.62). Among the models based on VIs + VIc + Rλ, the MLR model showed the highest R<sup>2</sup> c, followed by the SVMR model. However, there was overfitting in the SVMR model, with a small R<sup>2</sup> v; this can be attributed to the small number of red leaf spectra and a few outliers in the samples that affected the optimal classification hyperplane of the SVM. The most accurate Anth estimation model for red leaves was the MLR model based on VIs + VIc + Rλ (R<sup>2</sup> c = 0.85, R<sup>2</sup> v = 0.74), which can be used for the quantitative estimation of Anth in red leaves as a measure of MDMV infection severity.

The range of R<sup>2</sup> c and R<sup>2</sup> v values in the Anth models for healthy leaves was 0.62–0.68 and 0.60–0.66, respectively. Among the models based on VIs, the MLR model (R<sup>2</sup> c = 0.67, R<sup>2</sup> v = 0.64) showed the highest accuracy. Among the models based on VIc, the R<sup>2</sup> c and R<sup>2</sup> v of the MLR, PCA, and PLSR models were identical (R<sup>2</sup> c = 0.65, R<sup>2</sup> v = 0.64), and the modeling method showed little effect on accuracy. Among the models based on VIs + VIc + Rλ, the SVMR model showed the highest accuracy (R<sup>2</sup> c = 0.68, R<sup>2</sup> v = 0.66), which can be used to accurately estimate the Anth of healthy leaves for promptly monitoring the health status of maize.

In the distribution diagram of the measured and predicted values of red leaves, most points with small Anth were concentrated near the 1:1 line. However, the points with large Anth were distributed far from the 1:1 line, and the red leaf models showed satisfactory predictive performance for the small values of Anth but poor performance for large values. First of all, most of the leaf samples collected in this study were mildly infected with MDMV, and their Anth content was small. Only a few samples were seriously infected with MDMV and had high Anth. Moreover, MDMV-infected leaves were randomly collected in the entire study area, which had nothing to do with the fertilization situation in the plot and also resulted in the uneven distribution of sample data. As shown in Figure 9a, the model input parameter VIs includes a vegetation index with good effects in previous studies on the biophysical and biochemical parameters of healthy leaves (with low Anth content). It is not reconstructed for MDMV-infected leaves so that the model has a poor fitting effect on the high value of Anth. In the models of Figure 9b, only the reflectivity of 400–1000 nm was considered in the construction of the input parameter VIc, which did not make full use of all the spectral information that could be detected by the spectroradiometer. Therefore, the ability of these models to estimate Anth is limited. The model in Figure 9c uses Rλ + VIs + VIc as input to estimate Anth in red leaves. Compared with the model in Figure 9a,b, the accuracy is improved to some extent, but the good fitting effect is still a low Anth.

In the distribution diagram of the measured and predicted values of healthy leaves, all points were evenly distributed on both sides of the 1:1 line, and the healthy leaf models showed a better fit to the Anth values than the red leaf models. This is because healthy leaves were collected in plots with different fertilization; Anth data were evenly distributed and showed no obvious aggregation. Therefore, the models in Figure 9d–f had good fitting effects on both high and low values. MDMV-infected leaves were mainly distributed in the plots with 0 kg P2O5·ha−<sup>1</sup> + 90 kg <sup>N</sup>·ha−1, 60 kg P2O5·ha−<sup>1</sup> + 90 kgN·ha−1, 90 kg P2O5·ha−<sup>1</sup> + 90 kg <sup>N</sup>·ha−1, and 120 kg P2O5·ha−<sup>1</sup> + 90kg N·ha−1. It can be easily observed that the spatial distribution of MDMV-infected maize has a high degree of aggregation, but there is no obvious rule with the fertilization situation in the plots. Meanwhile, the results

also ruled out the possibility that phosphorus deficiency was responsible for the reddening of leaves in the study area.

**Figure 9.** Anth estimation models of red and healthy leaves. (**<sup>a</sup>**–**<sup>c</sup>**) represent MLR, PCR, PLSR, and SVMR models of red leaves Anth based on VIs, VIc, and Rλ + VIs + VIc, respectively. (**d**–**f**) show MLR, PCR, PLSR, and SVMR estimation models of healthy leaf Anth based on VIs, VIc, and Rλ + VIs + VIc, respectively.
