Towards Wheat Rust Disease Classification using Different Machine Learning Approaches: A Systematic Literature Review

This systematic literature review explores various machine learning (ML) approaches for the classification of wheat rust diseases, a significant threat to global food security. With the increasing demand for wheat due to population growth, the impact of diseases such as leaf rust and yellow rust, which contribute to substantial yield losses, necessitates effective and efficient detection methods. This review synthesizes existing research, highlighting the different types of wheat rust diseases, the ML techniques employed for their classification, and the performance parameters used to evaluate these models. The findings indicate the potential of AI-based techniques, particularly computer vision and deep learning, in enhancing disease identification and management strategies in agriculture. This review aims to provide insights into the effectiveness, limitations, and future directions of ML applications in wheat rust disease management.