A Review of Artificial Intelligence Techniques for Cotton Leaf Disease Identification

Abstract

Cotton is one of the most important cash crops worldwide, and its productivity is severely affected by leaf diseases that reduce yield and fiber quality. Traditional disease identification methods rely on expert knowledge and manual inspection, which are time-consuming, subjective, and often impractical for large-scale agricultural monitoring. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated, accurate, and scalable cotton leaf disease identification using image-based analysis. This review comprehensively analyzes state-of-the-art AI techniques employed for cotton leaf disease detection and classification. It covers conventional image processing approaches, handcrafted feature-based machine learning models, and modern deep learning architecture such as convolutional neural networks, transformers, ensemble learning, and explainable AI frameworks. Additionally, the role of publicly available datasets, data augmentation, lightweight models, and resource-efficient architectures is discussed. By synthesizing findings from recent literature, this review highlights key research trends, performance improvements, and practical limitations of existing approaches. The paper also identifies critical challenges and future research directions to support the development of robust, interpretable, and deployable AI-based systems for precision cotton agriculture.