Revolutionizing potato crop management: Deep learning-driven potato disease detection with convolutional neural networks

Abstract

Potato cultivation is essential for ensuring global food security, yet it faces significant threats from diseases such as early blight and late blight, resulting in substantial yield losses. To address this challenge, integrated disease management strategies are pivotal, encompassing cultural practices, disease-resistant varieties, and timely fungicide applications. Recent advancements in artificial intelligence (AI), particularly in deep learning, hold promise for revolutionizing disease detection in agriculture. This study aims to contribute to these efforts by developing a highly accurate and efficient system for early disease detection in potato crops using deep learning techniques. Through the utilization of convolutional neural networks (CNNs), transfer learning, and data augmentation, the proposed model showcases significant potential in automating the identification and classification of potato leaf diseases. Rigorous experimentation and evaluation demonstrate that the proposed CNN model achieved an impressive accuracy of 97.82% in classifying potato early and late blight diseases. These findings underscore the efficacy of CNNs in agricultural disease management and highlight the transformative role of AI technologies in bolstering global food security efforts.