An Approach Towards Identifying Bangladeshi Leaf Diseases through Transfer Learning and XAI

2025-05-21

AI Summary

To address low classification accuracy, poor model interpretability, and insufficient agronomic extension support for leaf disease diagnosis in Bangladeshi agriculture, this study develops a localized 21-class disease identification system covering six major crops—including rice and wheat. It introduces the first multimodal transfer learning framework in the Bengali agricultural context, integrating VGG19 and Xception architectures with five eXplainable AI (XAI) techniques—Grad-CAM, Layer-CAM, Score-CAM, Ablation-CAM, and Grad-CAM++. This synergy enables both high-accuracy classification and precise lesion localization via saliency heatmaps. The system achieves 98.90% classification accuracy on benchmark datasets. Heatmap visualizations significantly enhance diagnostic transparency, foster farmers’ trust in AI-driven decisions, and improve their practical adoption capability—thereby reducing reliance on specialized agricultural extension personnel. The end-to-end solution demonstrates strong feasibility for real-world deployment and scalable adoption across resource-constrained farming communities in Bangladesh.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Leaf diseases are harmful conditions that affect the health, appearance and productivity of plants, leading to significant plant loss and negatively impacting farmers' livelihoods. These diseases cause visible symptoms such as lesions, color changes, and texture variations, making it difficult for farmers to manage plant health, especially in large or remote farms where expert knowledge is limited. The main motivation of this study is to provide an efficient and accessible solution for identifying plant leaf diseases in Bangladesh, where agriculture plays a critical role in food security. The objective of our research is to classify 21 distinct leaf diseases across six plants using deep learning models, improving disease detection accuracy while reducing the need for expert involvement. Deep Learning (DL) techniques, including CNN and Transfer Learning (TL) models like VGG16, VGG19, MobileNetV2, InceptionV3, ResNet50V2 and Xception are used. VGG19 and Xception achieve the highest accuracies, with 98.90% and 98.66% respectively. Additionally, Explainable AI (XAI) techniques such as GradCAM, GradCAM++, LayerCAM, ScoreCAM and FasterScoreCAM are used to enhance transparency by highlighting the regions of the models focused on during disease classification. This transparency ensures that farmers can understand the model's predictions and take necessary action. This approach not only improves disease management but also supports farmers in making informed decisions, leading to better plant protection and increased agricultural productivity.

Problem

• Identify Bangladeshi leaf diseases using deep learning and XAI
• Classify 21 leaf diseases across six plants accurately
• Enhance transparency in disease detection for farmer understanding

Innovation

• Uses Transfer Learning models like VGG19 and Xception
• Applies Explainable AI techniques for model transparency
• Achieves high accuracy in leaf disease classification