EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea

Piyush Priya, Joe Johnson, Athimoolam Durgadevi iD, Navaneeth Vinayachandran, Meghna Pillai, Bharat Maitraya, Muthukumar V Bagavathiannan iD, Muthappa Senthil-Kumar iD

Applications in Plant Sciences · 30.10.2026

DOI: 10.1002/aps3.70075 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applications in Plant Sciences, online erschienen am 30.10.2026. Verfasst von Piyush Priya und 7 weiteren Autor:innen. Beteiligte Einrichtung: BRIC-National Institute of Plant Genome Research, Aruna Asaf Ali Marg 110067 New Delhi India. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Premise Dry root rot (DRR), an emerging global disease exacerbated by drought, affects a wide range of crops. The disease symptoms are manually scored for large‐scale germplasm screening to identify disease‐resistant varieties and test transgenic lines and other varieties. Despite its use in the past, manual disease identification is not only cumbersome but also often incapable of distinguishing between similar stress phenotypes. Manual disease scoring is tedious, time‐consuming, and often error‐prone, especially when screening large numbers of plants. To overcome this limitation, we developed a machine learning model that employs a learning‐based approach using convolutional neural networks for automated feature extraction and image‐based identification and severity assessment of DRR.

Methods

Our models were trained, tested, and validated using an in‐house dataset of 10,800 unique RGB images. A total of 51 deep learning models, including single‐task and multi‐task models, were developed using the Xception and Vision Transformer (ViT) architectures with standard image augmentations, and then validated on stratified independent test sets to demonstrate robustness across camera, scanner, and microscope modalities.

Results

The best multi‐task ViT model, capable of scoring across combined datasets, achieved 94% accuracy in distinguishing DRR from the control and had a root mean square error of 1 in predicting DRR severity score.

Discussion

This model's metrics, including confusion matrix performance, underscore its potential as an efficient and accessible tool for large‐scale germplasm screening for DRR, overcoming the challenges of manual scoring.

Schlagwörter

Stichwörter der Autor:innen

convolutional neural network (CNN)dry root rotimage‐based disease assessmentmachine learningresistant source identification

Autor:innen und Institutionen

  • BRIC-National Institute of Plant Genome Research, Aruna Asaf Ali Marg 110067 New Delhi India.
  • Department of Soil and Crop Sciences Texas A&M University College Station Texas USA.

ORCID-Profile: Athimoolam Durgadevi, Muthukumar V Bagavathiannan, Muthappa Senthil-Kumar

Zitieren

APA

Priya, P., Johnson, J., Durgadevi, A., Vinayachandran, N., Pillai, M., Maitraya, B., Bagavathiannan, M. V., & Senthil-Kumar, M. (2026). A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea. Applications in Plant Sciences. https://doi.org/10.1002/aps3.70075

Vancouver

Priya P, Johnson J, Durgadevi A, Vinayachandran N, Pillai M, Maitraya B, et al. A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea. Applications in Plant Sciences. 2026. doi:10.1002/aps3.70075

BibTeX
@article{Priya2026,
  author = {Priya, Piyush and Johnson, Joe and Durgadevi, Athimoolam and Vinayachandran, Navaneeth and Pillai, Meghna and Maitraya, Bharat and Bagavathiannan, Muthukumar V and Senthil-Kumar, Muthappa},
  title = {A multi‐task deep learning–based approach to identify and assess dry root rot disease in chickpea},
  journal = {Applications in Plant Sciences},
  year = {2026},
  doi = {10.1002/aps3.70075}
}
Kostenlos starten →