Dataset Information

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging.

ABSTRACT: Cotton is a significant economic crop. It is vulnerable to aphids (Aphis gossypii Glovers) during the growth period. Rapid and early detection has become an important means to deal with aphids in cotton. In this study, the visible/near-infrared (Vis/NIR) hyperspectral imaging system (376-1044 nm) and machine learning methods were used to identify aphid infection in cotton leaves. Both tall and short cotton plants (Lumianyan 24) were inoculated with aphids, and the corresponding plants without aphids were used as control. The hyperspectral images (HSIs) were acquired five times at an interval of 5 days. The healthy and infected leaves were used to establish the datasets, with each leaf as a sample. The spectra and RGB images of each cotton leaf were extracted from the hyperspectral images for one-dimensional (1D) and two-dimensional (2D) analysis. The hyperspectral images of each leaf were used for three-dimensional (3D) analysis. Convolutional Neural Networks (CNNs) were used for identification and compared with conventional machine learning methods. For the extracted spectra, 1D CNN had a fine classification performance, and the classification accuracy could reach 98%. For RGB images, 2D CNN had a better classification performance. For HSIs, 3D CNN performed moderately and performed better than 2D CNN. On the whole, CNN performed relatively better than conventional machine learning methods. In the process of 1D, 2D, and 3D CNN visualization, the important wavelength ranges were analyzed in 1D and 3D CNN visualization, and the importance of wavelength ranges and spatial regions were analyzed in 2D and 3D CNN visualization. The overall results in this study illustrated the feasibility of using hyperspectral imaging combined with multi-dimensional CNN to detect aphid infection in cotton leaves, providing a new alternative for pest infection detection in plants.

SUBMITTER: Yan T

PROVIDER: S-EPMC7917247 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of <i>Aphis gossypii</i> Glover Infection in Cotton Leaves Using Hyperspectral Imaging.

Yan Tianying T Xu Wei W Lin Jiao J Duan Long L Gao Pan P Zhang Chu C Lv Xin X

Frontiers in plant science 20210215

Cotton is a significant economic crop. It is vulnerable to aphids (<i>Aphis gossypii</i> Glovers) during the growth period. Rapid and early detection has become an important means to deal with aphids in cotton. In this study, the visible/near-infrared (Vis/NIR) hyperspectral imaging system (376-1044 nm) and machine learning methods were used to identify aphid infection in cotton leaves. Both tall and short cotton plants (Lumianyan 24) were inoculated with aphids, and the corresponding plants wit ...[more]

PMID: 33659014

Similar Datasets

Project description:BackgroundRNA interference (RNAi) is an effective tool to examine the function of individual genes. Carboxylesterases (CarE, EC 3.1.1.1) are known to play significant roles in the metabolism of xenobiotic compounds in many insect species. Previous studies in our laboratory found that CarE expression was up-regulated in Aphis gossypii (Glover) (Hemiptera: Aphididae) adults of both omethoate and malathion resistant strains, indicating the potential involvement of CarE in organophosphorus (OP) insecticide resistance. Functional analysis (RNAi) is therefore warranted to investigate the role of CarE in A. gossypii to OPs resistance.ResultCarE expression in omethoate resistant individuals of Aphis gossypii was dramatically suppressed following ingestion of dsRNA-CarE. The highest knockdown efficiency (33%) was observed at 72 h after feeding when dsRNA-CarE concentration was 100 ng/µL. The CarE activities from the CarE knockdown aphids were consistent with the correspondingly significant reduction in CarE expression. The CarE activity in the individuals of control aphids was concentrated in the range of 650-900 mOD/per/min, while in the individuals of dsRNA-CarE-fed aphids, the CarE activity was concentrated in the range of 500-800 mOD/per/min. In vitro inhibition experiments also demonstrated that total CarE activity in the CarE knockdown aphids decreased significantly as compared to control aphids. Bioassay results of aphids fed dsRNA-CarE indicated that suppression of CarE expression increased susceptibility to omethoate in individuals of the resistant aphid strains.ConclusionThe results of this study not only suggest that ingestion of dsRNA through artificial diet could be exploited for functional genomic studies in cotton aphids, but also indicate that CarE can be considered as a major target of organophosphorus insecticide (OPs) resistance in A. gossypii. Further, our results suggest that the CarE would be a propitious target for OPs resistant aphid control, and insect-resistant transgenic plants may be obtained through plant RNAi-mediated silencing of insect CarE expression.

Project description:BackgroundNeonicotinoid insecticides are applied worldwide for the control of agricultural insect pests. The evolution of neonicotinoid resistance has led to the failure of pest control in the field. The enhanced detoxifying enzyme activity and target mutations play important roles in the resistance of insects to neonicotinoid resistance. Emerging evidence indicates a central role of the gut symbiont in insect pest resistance to pesticides. Existing reports suggest that symbiotic microorganisms could mediate pesticide resistance by degrading pesticides in insect pests.ResultsThe 16S rDNA sequencing results showed that the richness and diversity of the gut community between the imidacloprid-resistant (IMI-R) and imidacloprid-susceptible (IMI-S) strains of the cotton aphid Aphis gossypii showed no significant difference, while the abundance of the gut symbiont Sphingomonas was significantly higher in the IMI-R strain. Antibiotic treatment deprived Sphingomonas of the gut, followed by an increase in susceptibility to imidacloprid in the IMI-R strain. The susceptibility of the IMI-S strain to imidacloprid was significantly decreased as expected after supplementation with Sphingomonas. In addition, the imidacloprid susceptibility in nine field populations, which were all infected with Sphingomonas, increased to different degrees after treatment with antibiotics. Then, we demonstrated that Sphingomonas isolated from the gut of the IMI-R strain could subsist only with imidacloprid as a carbon source. The metabolic efficiency of imidacloprid by Sphingomonas reached 56% by HPLC detection. This further proved that Sphingomonas could mediate A. gossypii resistance to imidacloprid by hydroxylation and nitroreduction.ConclusionsOur findings suggest that the gut symbiont Sphingomonas, with detoxification properties, could offer an opportunity for insect pests to metabolize imidacloprid. These findings enriched our knowledge of mechanisms of insecticide resistance and provided new symbiont-based strategies for control of insecticide-resistant insect pests with high Sphingomonas abundance.

Dataset Information

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of Aphis gossypii Glover Infection in Cotton Leaves Using Hyperspectral Imaging.

Publications

Combining Multi-Dimensional Convolutional Neural Network (CNN) With Visualization Method for Detection of <i>Aphis gossypii</i> Glover Infection in Cotton Leaves Using Hyperspectral Imaging.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets