Deep Learning-Based Barley Disease Quantification for Sustainable Crop Production.

Journal: Phytopathology
PMID:

Abstract

Net blotch disease caused by is a major fungal disease that affects barley () plants and can result in significant crop losses. In this study, we developed a deep learning model to quantify net blotch disease symptoms on different days postinfection on seedling leaves using Cascade R-CNN (region-based convolutional neural network) and U-Net (a convolutional neural network) architectures. We used a dataset of barley leaf images with annotations of net blotch disease to train and evaluate the model. The model achieved an accuracy of 95% for Cascade R-CNN in net blotch disease detection and a Jaccard index score of 0.99, indicating high accuracy in disease quantification and location. The combination of Cascade R-CNN and U-Net architectures improved the detection of small and irregularly shaped lesions in the images at 4 days postinfection, leading to better disease quantification. To validate the model developed, we compared the results obtained by automated measurement with a classical method (necrosis diameter measurement) and a pathogen detection by real-time PCR. The proposed deep learning model could be used in automated systems for disease quantification and to screen the efficacy of potential biocontrol agents to protect against disease.

Authors

  • Yassine Bouhouch
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Qassim Esmaeel
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Nicolas Richet
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Essaïd Aït Barka
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Aurélie Backes
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Luiz Angelo Steffenel
    Université de Reims Champagne Ardenne, LICIIS - LRC CEA DIGIT, 51100 Reims, France. Electronic address: angelo.steffenel@univ-reims.fr.
  • Majida Hafidi
    Faculté des sciences, Université Moulay Ismail, Laboratoire de biotechnologie végétale et de biologie moléculaire, B.P. 11201, Zitoune, Meknès, Maroc.
  • Cédric Jacquard
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.
  • Lisa Sanchez
    Université de Reims Champagne-Ardenne, Unité de recherche Résistance Induite et Bioprotection des Plantes (RIBP), EA 4707 USC INRAE 1488, Reims, France.