A Comprehensive Analysis of Deep Learning Techniques for Wheat Yellow Rust Disease Detection and Classification

Puccinia striiformis f. sp. tritici, the pathogen responsible for yellow rust in wheat, poses a significant threat to global wheat manufacture, causing substantial economic and agricultural losses. The timely and precise detection and classification of yellow rust are dangerous for implementing effective disease management strategies and minimizing crop damage. This review explores the latest advancements in wheat yellow rust detection, focusing on the integration of conventional approaches with cutting-edge machine learning (ML) and deep learning (DL) approaches. ML techniques, such as support vector machines (SVM) and random forests; have proven effective in analyzing spectral data for disease classification. Meanwhile, advanced DL methods, containing ResNet-50 and GhostNet-V2, demonstrated superior accuracy, with models achieving up to 96% in categorizing disease severity. These advancements highlight the transformative potential of DL methods in enhancing precision and competence in disease detection. This review provides a comprehensive evaluation of current methodologies and their outcomes, offering valuable insights for future research and practical applications in agricultural disease management.