Gray mold is one of the major diseases affecting tomato production. Its early symptoms are often inconspicuous, yet the disease spreads rapidly, leading to severe economic losses. Therefore, the development of efficient and non-destructive early detection technologies is of critical importance. At present, multispectral imaging-based detection methods are constrained by two major bottlenecks: limited sample size and single modality, which hinder precise recognition at the early stage of infection. To address these challenges, this study explores a detection approach integrating multispectral fluorescence and reflectance imaging, combined with machine learning algorithms, to enhance early recognition of tomato gray mold. Particular emphasis is placed on evaluating the effectiveness of multimodal information fusion in extracting early disease features, and on elucidating the quantitative relationships between disease progression and key physiological indicators such as chlorophyll content, water content, malondialdehyde levels, and antioxidant enzyme activities. Furthermore, an improved WGAN-GP (Wasserstein Generative Adversarial Network with Gradient Penalty) is employed to alleviate data scarcity under small-sample conditions. The results demonstrate that multimodal data fusion significantly improves model sensitivity to early-stage disease detection, while WGAN-GP-based data augmentation effectively enhances learning performance with limited samples. The Random Forest model achieved an early recognition precision of 97.21% on augmented datasets, and transfer learning models attained an overall precision of 97.56% in classifying different disease stages. This study provides an effective approach for the early prediction of tomato gray mold, with potential application value in optimizing disease management strategies and reducing environmental impact.

Peppers (Capsicum annuum L.) are among the most widely consumed vegetable globally and cultivated in large areas in China (Zhou and Zhou 2021). In December 2023, pepper pith necrosis was discovered in a field located in Haiwan Town, Haitang District, Sanya City, Hainan, China (109.69°N, 18.35°E), with an incidence of 15%. The lower leaves of diseased plants exhibited yellowing, and the stem epidermis degenerated, revealing aberrantly thickened and browning vascular tissue. Additionally, a small number of adventitious roots were observed on the stem. When main stems were longitudinally cut, a brown and disintegrated, partially hollow pith was observed. To isolate and identify the causal agent of pith necrosis in peppers, the border tissue between diseased and healthy areas was excised, sterilized by immersion in 70% ethanol for 1 minute, and then washed three times with sterile water. After drying, the treated tissues were cut into small pieces measuring 5 x 5 mm and cultured on Luria-Bertani agar (LB) medium. Following incubation at 28°C for 48 hours, isolation and purification of the bacteria obtained from the cultures were continued. After several purification, the colonies appeared yellow, circular, and smooth-margined. The cells obtained from colonies were negative for Gram staining and rod-shaped under the optical microscope. They were positive for catalase and urease but negative for oxidase and amylase, and were able to utilize L-arabinose, D-glucose and D-mannitol. Morphological, physiological and biochemical characteristics of the isolates resembled that of Pseudomonas sp.. To verify the species identity of the bacteria, genomic DNA from the isolated strain HN6 was extracted, and the universal primers 27F/1492R (Lane 1991) were used to amplify the 16S rRNA gene, while specific primers LAPS27/VIC4 (Mulet et al. 2010) and gyrBPF/gyrBPR (Yamamoto et al. 2000) were used to amplify the rpoB and gyrB genes. The BLASTn analysis of 16S rDNA, rpoB, and gyrB sequences showed strain HN6 (PQ374171, PQ393140, and PQ393141) had 100.00, 98.94% and 98.97% identity with P. oryzihabitans(CP044074). The phylogenetic analysis ( Mega 11 ) indicates that strain HN6 is clustered with P. oryzihabitans into one branch with Bootstrap supported 100 using the neighbor-joining method with 5,000 bootstrap replicates, further confirms that strain HN6 is most closely related to P. oryzihabitans. Therefore, strain HN6 was identified as P. oryzihabitans based on morphology, metabolic profile, and sequence analysis. Peppers were planted in non-porous pots containing sterilized substrates for the pathogenicity test. Sterile syringes were used to prick the stems near the roots of the peppers. The wounds were wrapped with sterile defatted cotton dipped in bacterial suspension ( 108 CFU / mL ). As a control, sterile defatted cotton soaked in sterile water was applied. Subsequently, the pots were covered with a plastic film to prevent contamination and moisturize. The temperature was maintained above 28°C, and moisture levels were kept consistent to support plant growth. Each treatment had 6 replicates. The 10-15 days post-treatment group showed symptoms at the inoculation site, including epidermal degeneration, thickened and browned vascular tissue and a disintegrated, hollow pith in the stems, while no symptoms were observed in the controls. Koch's postulates were fulfilled through the reisolation of the pathogen from infected tissues and subsequently identified as the same pathogenic bacterium using the aforementioned methods. While Pseudomonas syringae pv. syringae has been reported as the causative agent of leaf spot disease in peppers (Miller et al. 2010), this study presents the first report of P. oryzihabitans causing pith necrosis on pepper worldwide. P. oryzihabitans can cause rice panicle blight and grain discoloration (Hou et al. 2020), and has also found to caused center blackening disease (Choi et al. 2019) as well as stem and leaf rot (Li et al. 2021 ) on muskmelon. Pseudomonas sp. can causing leaf spot disease in peppers (Miller et al. 2010). As far as we know, this is the first Report of P. oryzihabitans causing pith necrosis on Pepper in China.

Bitter gourd, an important crop with both economic and medicinal value, requires precise identification of fruit shape and tubercle phenotypes to enhance breeding efficiency. To address the low efficiency and high subjectivity of traditional methods, this study proposes an improved YOLOv8-CEFC model for high-throughput automatic detection of the bitter gourd fruit shape and tubercle characteristics. First, the model integrates the ConvNeXt V2 module into the backbone network, combined with a Fully Convolutional Masked Autoencoder (FCMAE) framework and Global Response Normalization (GRN) layers to enhance feature extraction capabilities. Second, an Efficient Multi-scale Attention (EMA) mechanism is introduced, capturing local tubercle textures and global fruit shape contours simultaneously through a parallel dual-branch structure, while also improving the model’s robustness against cluttered backgrounds and environmental noise. Finally, Focal-CIoU Loss is incorporated to replace CIoU Loss, reducing the impact of class imbalance on model accuracy. The results show that the model achieves precision, recall, mAP50, mAP50-95, and F1 scores of 93.9%, 94.4%, 96.3%, 93.6%, and 94.15%, respectively, which represent improvements of 2.0%, 3.5%, 1.1%, 3.4%, and 2.75% compared to the original YOLOv8n model. The performance gain of the model was further examined using the bootstrap method, which confirmed that the improvement is statistically significant. Further validation through confusion matrix analysis, PR curves, and ablation experiments confirms the effectiveness of the improvements. Compared to other mainstream YOLO models, YOLOv8-CEFC demonstrates more accurate identification, better stability, and higher detection efficiency. The proposed improved YOLOv8-CEFC model provides an efficient solution for phenotypic analysis in Bitter Gourd breeding and holds significant importance for advancing the intelligentization of crop breeding.