Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease

Tomato yellow leaf curl disease (TYLCD), a devastating disease in tomato cultivation, causes reduced yields or even total crop failure in infected plants, severely compromising both productivity and quality. The prolonged asymptomatic infection period and non-distinct early symptoms of TYLCD impose...

Full description

Saved in:
Bibliographic Details
Main Authors: Junzhi Chen, Wenshan Zhong, Xuejun Yue, Ziyu Ding, Mengdan Du, Xuantian Li, Biao Chen, Haifeng Li, ZiFu He, Xiaoman She, Yafei Tang
Format: Article
Language:English
Published: Elsevier 2025-12-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S277237552500512X
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849236246803513344
author Junzhi Chen
Wenshan Zhong
Xuejun Yue
Ziyu Ding
Mengdan Du
Xuantian Li
Biao Chen
Haifeng Li
ZiFu He
Xiaoman She
Yafei Tang
author_facet Junzhi Chen
Wenshan Zhong
Xuejun Yue
Ziyu Ding
Mengdan Du
Xuantian Li
Biao Chen
Haifeng Li
ZiFu He
Xiaoman She
Yafei Tang
author_sort Junzhi Chen
collection DOAJ
description Tomato yellow leaf curl disease (TYLCD), a devastating disease in tomato cultivation, causes reduced yields or even total crop failure in infected plants, severely compromising both productivity and quality. The prolonged asymptomatic infection period and non-distinct early symptoms of TYLCD impose limitations on traditional detection methods, whereas hyperspectral imaging technology, capable of capturing rich spectral and spatial features, provides a technical foundation for early lesion identification and dynamic disease progression monitoring. This study proposes a spectral-spatial dual-branch residual network (SSDBRN) designed to fully extract and leverage complex features within hyperspectral images, aiming to achieve detection of TYLCD during its asymptomatic stage and classification of disease severity levels. Comparative experiments with three baseline models (2D CNN, 3D CNN, and HybridSN) demonstrated that SSDBRN achieved an early-infection detection accuracy of 84.2 % (5–7 days post-inoculation) and 96.2 % severity classification accuracy across six stages, significantly outperforming the baseline models. Furthermore, ablation studies validated the contributions of the key components of SSDBRN, namely the spectral channel attention module and the deformable convolution module, while generalization capability studies confirmed the model's robustness to complex backgrounds and lighting variations. Visualization analysis of spectral activation curves and spatial feature activation maps further elucidated the model's classification basis at both spectral and pixel-level dimensions. The findings establish that hyperspectral imaging integrated with SSDBRN enables non-destructive, early asymptomatic-stage detection and precise severity classification of TYLCD, providing an efficient diagnostic solution for the agricultural industry.
format Article
id doaj-art-32b5e34c242042ffa078f61e46a2bc13
institution Kabale University
issn 2772-3755
language English
publishDate 2025-12-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-32b5e34c242042ffa078f61e46a2bc132025-08-20T04:02:23ZengElsevierSmart Agricultural Technology2772-37552025-12-011210128110.1016/j.atech.2025.101281Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl diseaseJunzhi Chen0Wenshan Zhong1Xuejun Yue2Ziyu Ding3Mengdan Du4Xuantian Li5Biao Chen6Haifeng Li7ZiFu He8Xiaoman She9Yafei Tang10Guangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaGuangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaGuangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaGuangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; College of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaCollege of Electronic Engineering (College of Artificial Intelligence), South China Agricultural University, Guangzhou 510642, ChinaGuangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, ChinaGuangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Corresponding authors.Guangdong Provincial Key Laboratory of High Technology for Plant Protection, Plant Protection Research Institute, Guangdong Academy of Agricultural Sciences, Guangzhou 510640, China; Corresponding authors.Tomato yellow leaf curl disease (TYLCD), a devastating disease in tomato cultivation, causes reduced yields or even total crop failure in infected plants, severely compromising both productivity and quality. The prolonged asymptomatic infection period and non-distinct early symptoms of TYLCD impose limitations on traditional detection methods, whereas hyperspectral imaging technology, capable of capturing rich spectral and spatial features, provides a technical foundation for early lesion identification and dynamic disease progression monitoring. This study proposes a spectral-spatial dual-branch residual network (SSDBRN) designed to fully extract and leverage complex features within hyperspectral images, aiming to achieve detection of TYLCD during its asymptomatic stage and classification of disease severity levels. Comparative experiments with three baseline models (2D CNN, 3D CNN, and HybridSN) demonstrated that SSDBRN achieved an early-infection detection accuracy of 84.2 % (5–7 days post-inoculation) and 96.2 % severity classification accuracy across six stages, significantly outperforming the baseline models. Furthermore, ablation studies validated the contributions of the key components of SSDBRN, namely the spectral channel attention module and the deformable convolution module, while generalization capability studies confirmed the model's robustness to complex backgrounds and lighting variations. Visualization analysis of spectral activation curves and spatial feature activation maps further elucidated the model's classification basis at both spectral and pixel-level dimensions. The findings establish that hyperspectral imaging integrated with SSDBRN enables non-destructive, early asymptomatic-stage detection and precise severity classification of TYLCD, providing an efficient diagnostic solution for the agricultural industry.http://www.sciencedirect.com/science/article/pii/S277237552500512XTomato yellow leaf curl diseaseHyperspectral imagingDual-branch convolutional neural networkAsymptomatic disease period detectionClassification
spellingShingle Junzhi Chen
Wenshan Zhong
Xuejun Yue
Ziyu Ding
Mengdan Du
Xuantian Li
Biao Chen
Haifeng Li
ZiFu He
Xiaoman She
Yafei Tang
Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
Smart Agricultural Technology
Tomato yellow leaf curl disease
Hyperspectral imaging
Dual-branch convolutional neural network
Asymptomatic disease period detection
Classification
title Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
title_full Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
title_fullStr Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
title_full_unstemmed Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
title_short Hyperspectral imaging-driven deep learning approach: Asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
title_sort hyperspectral imaging driven deep learning approach asymptomatic stage detection and severity grading of tomato yellow leaf curl disease
topic Tomato yellow leaf curl disease
Hyperspectral imaging
Dual-branch convolutional neural network
Asymptomatic disease period detection
Classification
url http://www.sciencedirect.com/science/article/pii/S277237552500512X
work_keys_str_mv AT junzhichen hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT wenshanzhong hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT xuejunyue hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT ziyuding hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT mengdandu hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT xuantianli hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT biaochen hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT haifengli hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT zifuhe hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT xiaomanshe hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease
AT yafeitang hyperspectralimagingdrivendeeplearningapproachasymptomaticstagedetectionandseveritygradingoftomatoyellowleafcurldisease