*Article* **Identification and Severity Monitoring of Maize Dwarf Mosaic Virus Infection Based on Hyperspectral Measurements**

**Lili Luo, Qingrui Chang \*, Qi Wang and Yong Huang**

> College of Nature Resources and Environment, Northwest A&F University, Yangling 712100, China; lililuo@nwsuaf.edu.cn (L.L.); wangqieducation@nwsuaf.edu.cn (Q.W.); huangyong19920808@126.com (Y.H.) **\*** Correspondence: changqr@nwsuaf.edu.cn; Tel.: +86-1357-183-5969

**Abstract:** Prompt monitoring of maize dwarf mosaic virus (MDMV) is critical for the prevention and control of disease and to ensure high crop yield and quality. Here, we first analyzed the spectral differences between MDMV-infected red leaves and healthy leaves and constructed a sensitive index (SI) for measurements. Next, based on the characteristic bands (Rλ) associated with leaf anthocyanins (Anth), we determined vegetation indices (VIs) commonly used in plant physiological and biochemical parameter inversion and established a vegetation index (VIc) by utilizing the combination of two arbitrary bands following the construction principles of NDVI, DVI, RVI, and SAVI. Furthermore, we developed classification models based on linear discriminant analysis (LDA) and support vector machine (SVM) in order to distinguish the red leaves from healthy leaves. Finally, we performed UR, MLR, PLSR, PCR, and SVM simulations on Anth based on Rλ, VIs, VIc, and Rλ + VIs + VIc and indirectly estimated the severity of MDMV infection based on the relationship between the reflection spectra and Anth. Distinct from those of the normal leaves, the spectra of red leaves showed strong reflectance characteristics at 640 nm, and SI increased with increasing Anth. Moreover, the accuracy of the two VIc-based classification models was 100%, which is significantly higher than that of the VIs and Rλ-based models. Among the Anth regression models, the accuracy of the MLR model based on Rλ + VIs + VIc was the highest (R2c = 0.85; R2v = 0.74). The developed models could accurately identify MDMV and estimate the severity of its infection, laying the theoretical foundation for large-scale remote sensing-based monitoring of this virus in the future.

**Keywords:** plant disease; band selection; machine learning; anthocyanin; hyperspectral reflectance; linear discriminant analysis; precision crop protection
