Search

Abstract Background Pepper Phytophthora blight is a devastating disease during the growth process of peppers, significantly affecting their yield and quality. Accurate, rapid, and non-destructive early detection of pepper Phytophthora blight is of great importance for pepper production management. This study investigated the possibility of using multispectral imaging combined with machine learning to detect Phytophthora blight in peppers. Peppers were divided into two groups: one group was inoculated with Phytophthora blight, and the other was left untreated as a control. Multispectral images were collected at 0-h samples before inoculation and at 48, 60, 72, and 84 h after inoculation. The supporting software of the multispectral imaging system was used to extract spectral features from 19 wavelengths, and textural features were extracted using a gray-level co-occurrence matrix (GLCM) and a local binary pattern (LBP). The principal component analysis (PCA), successive projection algorithm (SPA), and genetic algorithm (GA) were used for feature selection from the extracted spectral and textural features. Two classification models were established based on effective single spectral features and significant spectral textural fusion features: a partial least squares discriminant analysis (PLS_DA) and one-dimensional convolutional neural network (1D-CNN). A two-dimensional convolutional neural network (2D-CNN) was constructed based on five principal component (PC) coefficients extracted from the spectral data using PCA, weighted, and summed with 19-channel multispectral images to create new PC images. Results The results indicated that the models using PCA for feature selection exhibit relatively stable classification performance. The accuracy of PLS-DA and 1D-CNN based on single spectral features is 82.6% and 83.3%, respectively, at the 48h mark. In contrast, the accuracy of PLS-DA and 1D-CNN based on spectral texture fusion reached 85.9% and 91.3%, respectively, at the same 48h mark. The accuracy of the 2D-CNN based on 5 PC images is 82%. Conclusions The research indicates that Phytophthora blight infection can be detected 48 h after inoculation (36 h before visible symptoms). This study provides an effective method for the early detection of Phytophthora blight in peppers.

Background: Pepper Phytophthora blight is a devastating disease during the growth process of peppers, significantly affecting their yield and quality. Accurate, rapid, and non-destructive early detection of pepper Phytophthora blight is of great importance for pepper production management. This study investigated the possibility of using multispectral imaging combined with machine learning to detect Phytophthora blight in peppers. Peppers were divided into two groups: one group was inoculated with Phytophthora blight, and the other was left untreated as a control. Multispectral images were collected at 0-h samples before inoculation and at 48, 60, 72, and 84 h after inoculation. The supporting software of the multispectral imaging system was used to extract spectral features from 19 wavelengths, and textural features were extracted using a gray-level co-occurrence matrix (GLCM) and a local binary pattern (LBP). The principal component analysis (PCA), successive projection algorithm (SPA), and genetic algorithm (GA) were used for feature selection from the extracted spectral and textural features. Two classification models were established based on effective single spectral features and significant spectral textural fusion features: a partial least squares discriminant analysis (PLS_DA) and one-dimensional convolutional neural network (1D-CNN). A two-dimensional convolutional neural network (2D-CNN) was constructed based on five principal component (PC) coefficients extracted from the spectral data using PCA, weighted, and summed with 19-channel multispectral images to create new PC images. Results: The results indicated that the models using PCA for feature selection exhibit relatively stable classification performance. The accuracy of PLS-DA and 1D-CNN based on single spectral features is 82.6% and 83.3%, respectively, at the 48h mark. In contrast, the accuracy of PLS-DA and 1D-CNN based on spectral texture fusion reached 85.9% and 91.3%, respectively, at the same 48h mark. The accuracy of the 2D-CNN based on 5 PC images is 82%. Conclusions: The research indicates that Phytophthora blight infection can be detected 48 h after inoculation (36 h before visible symptoms). This study provides an effective method for the early detection of Phytophthora blight in peppers. [ABSTRACT FROM AUTHOR]

The population structure of Phytophthora capsici among asexual and sexual progenies was analyzed using ISSR. Thirty asexual progenies of one parent and three sexual populations were assayed for genetic diversity using 5 ISSR primers and DNA from 120 offspring of P. capsici was amplified. In total, 71 reproducible ISSR fragments were obtained, of which 100% were polymorphic, revealing high polymorphism among the isolates. Among them, the percentages of polymorphism of sexual and asexual progeny isolates were 100.00 and 77.46%, respectively. Genetic similarity coefficients among all the isolates ranged from 0.54 to 0.73. The sexual offspring population showed much more variability than the asexual offspring population with 76.26% variability attributed to diversity within populations as compared with 23.74% among populations. This research reveals that the sexual progeny population of P. capsici contributes more genetic diversity than that of asexual progeny population.

Copyright of Journal of Southern Agriculture is the property of Journal of Southern Agriculture and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Two endophytic bacterial strains, Fy11 and Zy44 ( Bacillus amyloliquefaciens ), isolated from Ginkgo biloba leaves, were tested as a single application and in combination for their abilities to suppress pepper phytophthora blight under greenhouse conditions. When both strains were applied in a mixture, the disease severity was more reduced. The objective of this study was to find out the inhibitory mechanisms of synergistic activity against pepper phytophthora blight through a mixture of Fy11 + Zy44. Firstly, the colonization ability of the two endophytic bacterial strains was tested in pepper tissues. The result indicated that both endophytic strains were efficient colonizers of pepper, and could vertically transfer from roots to shoots and leaves. After inoculation for 7 days, the population densities of Fy11- gfp and Zy44- gfp were 24.7 × 10 3 CFU/g FW and 13.0 × 10 3 CFU/g FW in pepper roots, respectively. The cell counts of co-inoculated Fy11 + Zy44 were not significant different comparing to a single strain inter pepper tissues. Secondly, the direct antagonism of antifungal compounds produced by the endophytic bacteria were investigated against pepper phytophthora blight. The crude lipopeptides produced by strain Zy44 highly effectively reduced disease index, and the control efficacy reached 84.8% and 67.2% in 7 d and 15 d after inoculation with the pathogen, respectively. The control effect of the secondary metabolites produced by strain Fy11 was not obvious. In the end, the induced systemic resistance (ISR) mediated by strains Fy11 and Zy44 on pepper were further analysed using priming effect of the defense-related genes after pathogen challenge. The expressions of CaPR4 ( Capsicum annuum pathogenesis-protein 4) and CaBGLU ( C. annuum β -1,3-glucanase) were strongly induced in the plants treated with strain Fy11 in 24 h after pathogen challenge, but CaPR4 and CaBGLU transcripts were not increased in the plants treated with strain Zy44. These results indicated that the mechanisms of additive effect through combined strains Zy44 and Fy11 might be due to direct antagonism of antifungal lipopeptides produced by strain Zy44, as well as indirect inhibition through ISR induced by strain Fy11. Therefore, the synergistic interactions were due to the summation of biocontrol mechanisms of both biocontrol agents. This work provides a theoretical explanation for our findings of reduced disease severity with a mixture of endophytic bacteria. [ABSTRACT FROM AUTHOR]