Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Explainable CNN framework for accurate crop disease detection using plant leaf images.

Avik Ray1, Tamilarasi Kathirvel Murugan2, Logeswari Govindaraj1

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, 600127, India.

Scientific Reports
|June 16, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Light Acquisition02:16

Light Acquisition

In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Impact of Treatment Sequencing With CAR T-cell Therapies and Bispecific Antibodies on Long-term Survival in 4L+ RRMM in the United States: A Simulation Model.

Clinical lymphoma, myeloma & leukemia·2026
Same author

Early prediction and risk assessment of adverse drug combinations using ensemble learning.

Scientific reports·2026
Same author

Enhancing underwater sensor network security using QKD-enabled acoustic-optical hybrid communication.

Scientific reports·2026
Same author

Explainable multimodal feature fusion networks for Parkinson's disease prediction.

Frontiers in digital health·2026
Same author

Adversarial robust EEG-based brain-computer interfaces using a hierarchical convolutional neural network.

Scientific reports·2026
Same author

Comparative Effectiveness of Current Glucose-lowering Medications in Type 2 Diabetes Mellitus: Emulation of a Modified GRADE Trial.

Journal of general internal medicine·2026

This study introduces an explainable, lightweight deep learning model for fast and accurate crop disease identification using leaf images. This AI tool enhances agricultural efficiency and food security by enabling real-time, interpretable plant disease diagnosis.

Area of Science:

  • Agricultural Science
  • Computer Science
  • Artificial Intelligence

Background:

  • Traditional crop disease diagnosis is time-consuming, requires expertise, and is unsuitable for large-scale farming.
  • Early and accurate disease detection is crucial for agricultural output, cost reduction, and food security.

Purpose of the Study:

  • To develop an explainable, lightweight Convolutional Neural Network (CNN)-based model for crop disease identification using RGB leaf images.
  • To enhance feature extraction efficiency and reduce computational load for practical agricultural applications.

Main Methods:

  • The model incorporates depth-wise separable convolution, SE blocks, skip connections, and guided attention for feature learning.
  • Gradient-weighted Class Activation Mapping (Grad-CAM) is employed for visualizing affected leaf areas, improving model interpretability.
Keywords:
Convolutional Neural NetworksDeep learningExplainable AIGrad-CAMImage classificationPlant disease detectionPlantVillage datasetPrecision agriculture

Related Experiment Videos

  • The model was trained and validated on the PlantVillage dataset (54,305 images, 38 diseases, 14 crops).

    • Main Results:

    • Achieved high accuracies: 97.6% (training), 88.3% (validation), and 97.63% (testing).
    • Demonstrated strong performance with Macro-F1 score of 0.867 and Micro-ROC-AUC of 0.99.
    • The lightweight model offers built-in interpretability, suitable for mobile and edge devices.

    Conclusions:

    • The developed CNN model is an effective and interpretable tool for real-time plant disease diagnosis.
    • Its lightweight architecture and interpretability make it suitable for edge-enabled agriculture.
    • The approach contributes to improving agricultural sustainability and food security through advanced diagnostics.