Role of Artificial Intelligence in Plant Disease Detection: A Review

Abstract

Agriculture is the backbone of human civilization, playing a vital role in sustaining national economies. Enhancing food production is crucial for mitigating hunger and ensuring global food security. However, plant diseases caused by fungi, bacteria, viruses, and nematodes pose a significant threat to agricultural productivity, resulting in substantial economic losses worldwide. Effective crop protection and improvement of crop quality and quantity are inextricably linked to plant disease management. Accurate identification and detection of plant diseases are essential for devising strategic control measures. Traditional disease detection methods have proven inadequate, with delayed diagnosis and inaccurate results hindering effective disease control. Recent advances in Artificial Intelligence (AI) have revolutionized plant disease detection, enabling rapid and accurate identification of diseases across vast areas. This review aims to investigate the efficacy of automated plant disease detection using Machine Learning (ML), Deep Learning (DL), and Hyperspectral Imaging. By leveraging these cutting-edge technologies, we can develop more accurate and reliable disease detection systems, ultimately contributing to enhanced crop yields and global food security.

Code and data availability

This is a review article on AI in plant disease detection. It describes general ML/DL pipelines and cites prior studies (e.g., PlantVillage dataset usage by other authors), but presents no paper-specific phenotype datasets, images, code, models, or supplements with availability statements. The PlantVillage dataset is a

No evidence-backed public reproduction asset is currently recorded.