A Novel Real-Time Deep Learning Method for Identifying Potato Plant Diseases

Abstract

Introduction: This research aims to develop an advanced deep learning (DL) model for the accurate detection of potato leaf diseases, specifically Early Blight and Late Blight, which significantly affect crop yield in India. By modifying the DenseNet architecture, the proposed model achieves an accuracy of 99.54%, surpassing previous benchmarks. A mobile app has also been introduced to assist farmers with real-time disease diagnosis, actionable solutions, and expert consultation, thereby improving overall crop management and food security. Artificial Intelligence (AI) and deep learning provide promising solutions for accurate and efficient disease detection. Methods: This study proposes a novel deep learning approach that modifies the DenseNet architecture for improved disease classification. The model was trained on a dataset of potato leaf images, leveraging image processing and deep learning techniques to enhance detection accuracy. Results: The modified Dense-Net model achieved a classification accuracy of 99.54%, outperforming previous existing literature. This significant improvement underscores the robustness and reliability of the proposed approach in effectively detecting potato plant diseases. Discussions: The proposed model achieves a high accuracy of 99.54%, surpassing previous approaches and demonstrating significant advancement in potato disease detection. Its integration into a mobile app bridges the gap between AI research and practical farming applications, offering real-time diagnosis and expert support. However, limitations such as dataset variability and the need for broader field validation remain, highlighting the importance of continuous model updates and testing. Conclusion: To aid farmers, a user-friendly mobile application powered by a deep learning model was developed. The app provides disease diagnosis, treatment recommendations, and real- time consultations with certified agronomists. This AI-driven tool enhances accessibility and decision-making for farmers, promoting sustainable agricultural practices.

Plant phenotyping relevance

ジャガイモ葉画像から植物病害状態を推定する深層学習手法を開発・評価しており、植物フェノタイピングが中心的である。

Code and data availability

The supplied blocks contain only a Bentham Science advertising/media pack (journal lists, reader demographics, impact factors) and no article content, datasets, images, code, models, or data availability statements related to the paper's potato disease phenotyping or analysis. No qualifying paper-specific assets are in

No evidence-backed public reproduction asset is currently recorded.