Tobacco Mosaic Virus (TMV) and Potato Virus Y (PVY) pose significant threats to crop production. Non-destructive and accurate surveillance is crucial to effective disease control. In this study, we propose the adoption of hyperspectral and machine learning technologies to discern the type and severity of tobacco leaves affected by PVY and TMV infection. Initially, we applied three preprocessing methods – Multivariate Scattering Correction (MSC), Standard Normal Variate (SNV), and Savitzky-Golay smoothing filter (SavGol) – to corrected the leaf full-length spectral sheet data (350-2500nm). Subsequently, we employed two classifiers, support vector machine (SVM) and random forest (RF), to establish supervised classification models, including binary classification models (healthy/diseased leaves or PVY/TMV infected leaves) and six-class classification models (healthy and various severity levels of diseased leaves). Based on the core evaluation index, our models achieved accuracies in the range of 91–100% in the binary classification. In general, SVM demonstrated superior performance compared to RF in distinguishing leaves infected with PVY and TMV. Different combinations of preprocessing methods and classifiers have distinct capabilities in the six-class classification. Notably, SavGol united with SVM gave an excellent performance in the identification of different PVY severity levels with 98.1% average precision, and also achieved a high recognition rate (96.2%) in the different TMV severity level classifications. The results further highlighted that the effective wavelengths captured by SVM, 700nm and 1800nm, would be valuable for estimating disease severity levels. Our study underscores the efficacy of integrating hyperspectral technology and machine learning, showcasing their potential for accurate and non-destructive monitoring of plant viral diseases.

Long-term and extensive use of chemical pesticides has led to the development of resistance in many important agricultural pests. The mechanisms of resistance formation in pests are complex and variable, and unraveling the resistance mechanisms is the key to control resistant pests. Insect cuticle, as the first line of defense for insecticides, plays a non-negligible role in insecticide penetration resistance. Although penetration resistance is widespread in insects, the multiple molecular mechanisms that impede insecticide penetration are unclear, especially in Spodoptera litura. This study aims to reveal the molecular mechanisms of insecticide penetration resistance in S. litura. The structure and thickness of cuticle were analyzed by TEM, and the role of cuticle in penetration resistance was determined by different application methods. The molecular mechanism of cuticular proteins overexpression was analyzed using RNAi, TEM, dual-luciferase assay and EMSA from cis- and trans-acting factors. In addition, the relationship between the chitin synthetic pathway and insecticide resistance was explored through enzyme activity, inhibitor assay, molecular docking and RNAi. Furthermore, the role of 20E in penetration resistance was analyzed. The cuticle of the resistant populations was significantly thickened and accompanied by extrusion, which contributed significantly to indoxacarb resistance. Constitutive upregulation of trans-acting factor SlituFTZ-F1 co-regulates the overexpression of SlituCP26 with cis-acting elements in the SlituCP26 promoter (74 bp insertion), affecting the cuticle thickness‑mediated indoxacarb penetration resistance. Meanwhile, the overexpression of key genes in the chitin synthesis pathway increased the chitin content, which combined with SlituCP26 to participate in indoxacarb resistance. Moreover, 20E affected the SlituFTZ-F1-mediated regulatory pathway and chitin biosynthesis pathway in indoxacarb resistance. This study comprehensively elucidated the molecular mechanism of cuticle thickening mediating penetration resistance to indoxacarb and confirmed its existence in the field populations of S. litura.