Classification models for Tobacco Mosaic Virus and Potato Virus Y using hyperspectral and machine learning techniques

Discrimination of leaf diseases in Maize/Soybean intercropping system based on hyperspectral imaging

In order to achieve precise discrimination of leaf diseases in the Maize/Soybean intercropping system, i.e. leaf spot disease, rust disease, mixed leaf diseases, this study utilized hyperspectral imaging and deep learning algorithms for the classification of diseased leaves of maize and soybean. In the experiments, hyperspectral imaging equipment was used to collect hyperspectral images of leaves, and the regions of interest were extracted within the spectral range of 400 to 1000 nm. These regions included one or more infected areas on the leaves to obtain hyperspectral data. This approach aimed to enhance the accurate discrimination of different types of diseases, providing more effective technical support for the detection and control of crop diseases. The preprocessing of hyperspectral data involved four methods: Savitzky-Golay (SG), Standard Normal Variate (SNV), Multiplicative Scatter Correction (MSC) and 1st Derivative (1st Der). The 1st Der was found to be the optimal preprocessing method for hyperspectral data of maize and soybean diseases. Competitive Adaptive Reweighted Sampling (CARS), Successive Projections Algorithm (SPA) and Principal Component Analysis (PCA) were employed for feature extraction on the optimal preprocessed data. The Support Vector Machines (SVM), Bidirectional Long Short-Term Memory Network (BiLSTM) and Dung Beetle Optimization-Bidirectional Long Short-Term Memory Network (DBO-BiLSTM) were established for the discrimination of maize and soybean diseases. Comparative analysis indicated that, in the classification of maize and soybean diseases, the DBO-BiLSTM model based on the CARS extraction method (1st Der-CARS-DBO-BiLSTM) demonstrated the highest classification rate, reaching 98.7% on the test set. The research findings suggest that integrating hyperspectral imaging with both traditional and deep learning methods is a viable and effective approach for classifying diseases in the intercropping model of maize and soybean. These results offer a novel method and a theoretical foundation for the non-invasive, precise, and efficient identification of diseases in the intercropping model of maize and soybean, carrying positive implications for agricultural production.

Streptomyces fradiae Mitigates the Impact of Potato Virus Y by Inducing Systemic Resistance in Two Egyptian Potato (Solanum tuberosum L.) Cultivars

In this study, the impact of culture media filtrate of QD3 actinobacterial isolate on two potato cultivars, Spunta and Diamond, infected with potato virus Y (PVY) was investigated. Various parameters, including infection percentage, PVY virus infectivity, disease severity scoring, PVY optical density, photosynthetic and defense-related biochemical markers, enzymatic profiling, phenolic compounds, proline content, salicylic acid levels, and growth and yield parameters, were assessed to elucidate the potential of the QD3 actinobacterial isolate culture filtrate in mitigating PVY-induced damage. The physiological and biochemical characteristics of the QD3 actinobacterial isolate, including its salinity tolerance, pH preferences, and metabolic traits, were investigated. Molecular identification via 16S rRNA gene sequencing confirmed its classification as Streptomyces fradiae QD3, and it was deposited in GenBank with the gene accession number MN160630. Distinct responses between Spunta and Diamond cultivars, with Spunta displaying greater resistance to PVY infection. Notably, pre-infection foliar application of the QD3 filtrate significantly reduced disease symptoms and virus infection in both cultivars. For post-PVY infection, the QD3 filtrate effectively mitigated disease severity and the PVY optical density. Furthermore, the QD3 filtrate positively influenced photosynthetic pigments, enzymatic antioxidant activities, and key biochemical components associated with plant defense mechanisms. Gas chromatography‒mass spectrometry (GC‒MS) analysis revealed palmitic acid (hexadecanoic acid, methyl ester) and oleic acid (9-octadecanoic acid, methyl ester) as the most prominent compounds, with retention times of 23.23 min and 26.41 min, representing 53.27% and 23.25%, respectively, of the total peak area as primary unsaturated fatty acids and demonstrating antiviral effects against plant viruses. Cytotoxicity assays on normal human skin fibroblasts (HSFs) revealed the safety of QD3 metabolites, with low discernible toxicity at high concentrations, reinforcing their potential as safe and effective interventions. The phytotoxicity results indicate that all the seeds presented high germination rates of approximately 95-98%, suggesting that the treatment conditions had no phytotoxic effect on the Brassica oleracea (broccoli) seeds, Lactuca sativa (lettuce) seeds, and Eruca sativa (arugula or rocket) seeds. Overall, the results of this study suggest that the S. fradiae filtrate has promising anti-PVY properties, influencing various physiological, biochemical, and molecular aspects in potato cultivars. These findings provide valuable insights into potential strategies for managing PVY infections in potato crops, emphasizing the importance of Streptomyces-derived interventions in enhancing plant health and crop protection.

Research Progress on Plant Responses to Stress Combinations in the Context of Climate Change

In the context of climate change, the frequency and intensity of extreme weather events are increasing, environmental pollution and global warming are exacerbated by anthropogenic activities, and plants will experience a more complex and variable environment of stress combinations. Research on plant responses to stress combinations is crucial for the development and utilization of climate-adaptive plants. Recently, the concept of stress combinations has been expanded from simple to multifactorial stress combinations (MFSCs). Researchers have realized the complexity and necessity of stress combination research and have extensively employed composite gradient methods, multi-omics techniques, and interdisciplinary approaches to integrate laboratory and field experiments. Researchers have studied the response mechanisms of plant reactive oxygen species (ROS), phytohormones, transcription factors (TFs), and other response mechanisms under stress combinations and reached some generalized conclusions. In this article, we focus on the research progress and methodological dynamics of plant responses to stress combinations and propose key scientific questions that are crucial to address, in the context of plant responses to stress assemblages, conserving biodiversity, and ensuring food security. We can enhance the search for universal pathways, identify targets for stress combinations, explore adaptive genetic responses, and leverage high-technology research. This is in pursuit of cultivating plants with greater tolerance to stress combinations and enabling their adaptation to and mitigation of the impacts of climate change.