Classifying early-stage soybean fungal diseases on hyperspectral images using convolutional neural networks

dc.contributor.authorHsiao, Chieh Fu
dc.contributor.authorFeyrer, Georg
dc.contributor.authorStein, Anthony
dc.date.accessioned2025-06-06T08:21:49Z
dc.date.available2025-06-06T08:21:49Z
dc.date.issued2025
dc.description.abstractUsing convolutional neural networks (CNNs) to detect plant diseases has proven to reach high accuracy in the classification of infected and non-infected plant images. However, most of the existing researches are based on RGB images due to the availability and the comparably low cost of image collection. The limited spectral information restricts the detectability of plant diseases, especially in the early stage where often symptoms of pathogen infection have not yet become visible. To this end, in this study, hyperspectral imaging (HSI) data are combined with deep learning models to test the classification ability of two soybean fungal diseases: Asian soybean rust (Phakopsora pachyhizi) and soybean stem rust (Sclerotinia scleroriorum). Different CNNs employing 2D, 3D convolution, and hybrid approaches are compared. The influences of the depth of the convolutional layer and the regularization techniques are also discussed. Besides, image augmentation methods are investigated to overcome the problem of data scarcity. The results indicate the 6-convolutional-layer depth hybrid model to have the best capacity in classifying Asian soybean rust in the early-mid to mid-late stage when there are over 2 % visible symptoms but a limited detectability in the early stages when there are below 2 % visible symptoms on leaves. On the other hand, the optimized CNN model shows a limited capability to detect both diseases when there are no visible symptoms observable. Overall, this study suggests a hybrid 2D-3D convolutional model with augmentation and regularization methods has a high potential in the early detection of fungal diseases. This research is expected to contribute to a new cropping system that vastly reduces the chemical-synthesis plant protection products, where a continuous pathogen disease monitoring plays a key to manage the crop stands.en
dc.identifier.urihttps://hohpublica.uni-hohenheim.de/handle/123456789/17754
dc.identifier.urihttps://doi.org/10.1016/j.atech.2025.101023
dc.language.isoeng
dc.rights.licensecc_by
dc.subjectHyperspectral images
dc.subjectSoybean
dc.subjectFungal diseases
dc.subjectEarly detection
dc.subjectDeep learnin
dc.subjectPathogen detection
dc.subject.ddc630
dc.titleClassifying early-stage soybean fungal diseases on hyperspectral images using convolutional neural networksen
dc.type.diniArticle
dcterms.bibliographicCitationSmart agricultural technology, 11 (2025), 101023. https://doi.org/10.1016/j.atech.2025.101023. Amsterdam : Elsevier
dcterms.bibliographicCitation.articlenumber101023
dcterms.bibliographicCitation.journaltitleSmart agricultural technology
dcterms.bibliographicCitation.originalpublishernameElsevier
dcterms.bibliographicCitation.originalpublisherplaceAmsterdam
dcterms.bibliographicCitation.volume11
local.export.bibtex@article{Hsiao2025, doi = {10.1016/j.atech.2025.101023}, url = {https://hohpublica.uni-hohenheim.de/handle/123456789/17754}, author = {Hsiao, Chieh Fu and Feyrer, Georg and Stein, Anthony et al.}, title = {Classifying early-stage soybean fungal diseases on hyperspectral images using convolutional neural networks}, journal = {Smart agricultural technology}, year = {2025}, volume = {11}, }
local.export.bibtexAuthorHsiao, Chieh Fu and Feyrer, Georg and Stein, Anthony et al.
local.export.bibtexKeyHsiao2025
local.export.bibtexType@article
local.title.fullClassifying early-stage soybean fungal diseases on hyperspectral images using convolutional neural networks

Files

Original bundle

Now showing 1 - 2 of 2
Loading...
Thumbnail Image
Name:
1-s2.0-S2772375525002564-main.pdf
Size:
8 MB
Format:
Adobe Portable Document Format
No Thumbnail Available
Name:
1-s2.0-S2772375525002564-mmc1.docx
Size:
30.98 KB
Format:
Microsoft Word XML

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
7.85 KB
Format:
Item-specific license agreed to upon submission
Description: