Related Experiment Video
Updated: May 27, 2025
08:20
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
Published on: October 27, 2023
1.3K
Deep learning and explainable AI for classification of potato leaf diseases.
Sarah M Alhammad1, Doaa Sami Khafaga1, Walaa M El-Hady2
1Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia.
Frontiers in Artificial Intelligence
|February 18, 2025
Summary
This study introduces an advanced deep learning model for classifying potato leaf diseases using transfer learning and Explainable AI (XAI). The model achieved high accuracy, aiding crop health management.
Area of Science:
- Agricultural Science
- Computer Science
- Artificial Intelligence
Background:
- Accurate potato leaf disease classification is crucial for crop health and productivity.
- Existing methods may lack transparency and struggle with limited data.
Purpose of the Study:
- To develop a unified approach for potato leaf disease classification using deep learning.
- To integrate Explainable AI (XAI) for model interpretability and trust.
- To enhance predictive performance and agricultural integration.
Main Methods:
- A transfer learning-based deep learning model was developed for potato leaf disease classification.
- Explainable AI techniques, specifically gradient-weighted class activation mapping (Grad-CAM), were applied.
- The model was trained and validated on a publicly available potato leaf disease dataset.
Main Results:
- The model achieved 97% validation accuracy and 98% testing accuracy.
- Explainable AI provided interpretable insights into the model's decision-making process.
- The approach demonstrated effectiveness in classifying potato leaf diseases.
Conclusions:
- The proposed model effectively classifies potato leaf diseases with high accuracy.
- Explainable AI enhances the transparency and usability of deep learning models in agriculture.
- This unified approach supports improved crop management and disease identification.
