A Review of Artificial Intelligence Techniques for Rice Leaf Disease Detection and Classification

Abstract

Rice leaf diseases significantly threaten global rice production, directly affecting crop yield, quality, and food security. Early and accurate detection of these diseases is therefore essential for effective crop management and sustainable agriculture. Recent advances in artificial intelligence (AI), particularly machine learning (ML) and deep learning (DL), have enabled automated, efficient, and scalable solutions for rice leaf disease detection and classification. This review provides a comprehensive analysis of existing AI-based techniques applied to rice leaf disease diagnosis, covering traditional image processing methods, classical ML classifiers, and state-of-the-art DL architectures such as convolutional neural networks, transfer learning models, and hybrid frameworks. Publicly available datasets, data augmentation strategies, and evaluation metrics commonly used in the literature are also discussed. Furthermore, the review critically examines key challenges, including limited labeled data, class imbalance, environmental variability, and poor generalization under real-field conditions. Special attention is given to recent trends involving explainable AI, lightweight models for edge deployment, and multi-disease classification systems. By identifying research gaps and limitations in current approaches, this review highlights future directions toward robust, interpretable, and real-time AI-driven solutions for rice leaf disease detection. The insights presented aim to support researchers and practitioners in developing reliable decision-support systems for precision agriculture and sustainable rice production.