Plant Disease Detection Using Machine Learning

Abstract

The exploration of integrating machine learning in plant disease detection delves into its evolution, applications, and transformative impact on global agriculture, emphasizing models like Support Vector Machines and Convolutional Neural Networks. This study explores the fundamental ideas within plant pathology, including various diseases and their symptoms, and underscores the critical nature of prompt diagnosis. It contrasts traditional strategies with cutting-edge machine learning techniques to pinpoint the shortcomings of older methods and emphasize the benefits offered by modern technology. The discussion extends to data collection, preprocessing techniques, and diverse machine learning models, offering valuable insights for agricultural implementation. By examining evaluation metrics and outlining future research directions, the study provides a roadmap for researchers, practitioners, and technology developers, calling for the seamless integration of machine learning to achieve sustainable, resilient, and productive global agricultural practices. © 2025 selection and editorial matter, Madhumathi Ramasamy, Karthigha Mohan, Pethuru Raj Chelliah, and Kai Sheng.