Explainable AI-Enhanced Deep Learning for Pumpkin Leaf Disease Detection: A Comparative Analysis of CNN Architectures

2025-01-09

AI Summary

To address agricultural productivity loss caused by pumpkin leaf diseases, this work introduces the Pumpkin Leaf Disease Dataset—a curated collection of 2,000 high-resolution images covering five major diseases, including downy mildew. We systematically benchmark seven CNN architectures for disease classification. For the first time in this domain, we integrate multiple eXplainable AI (XAI) techniques—Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM—to enhance model interpretability and foster trust among agricultural practitioners. ResNet50 achieves the best overall performance with 90.5% classification accuracy and balanced metrics across all disease classes. XAI visualizations precisely localize pathogenic lesions, confirming the biological plausibility of model decisions. This study delivers a high-accuracy, interpretable, and field-deployable framework for early-stage intelligent diagnosis of pumpkin leaf diseases.

Technology Category

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

Application Category

• Responsible Web: Algorithmic accountability and transparency on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Pumpkin leaf diseases are significant threats to agricultural productivity, requiring a timely and precise diagnosis for effective management. Traditional identification methods are laborious and susceptible to human error, emphasizing the necessity for automated solutions. This study employs on the"Pumpkin Leaf Disease Dataset", that comprises of 2000 high-resolution images separated into five categories. Downy mildew, powdery mildew, mosaic disease, bacterial leaf spot, and healthy leaves. The dataset was rigorously assembled from several agricultural fields to ensure a strong representation for model training. We explored many proficient deep learning architectures, including DenseNet201, DenseNet121, DenseNet169, Xception, ResNet50, ResNet101 and InceptionResNetV2, and observed that ResNet50 performed most effectively, with an accuracy of 90.5% and comparable precision, recall, and F1-Score. We used Explainable AI (XAI) approaches like Grad-CAM, Grad-CAM++, Score-CAM, and Layer-CAM to provide meaningful representations of model decision-making processes, which improved understanding and trust in automated disease diagnostics. These findings demonstrate ResNet50's potential to revolutionize pumpkin leaf disease detection, allowing for earlier and more accurate treatments.

Problem

• pumpkin leaf diseases
• deep learning models
• automated identification

Innovation

• Deep Learning Models
• Explainable AI (XAI)
• Agricultural Technology