Enhancing Rice Crop Health through Computational Intelligence-Based Disease Detection

Abstract

Rice is one of the most important staple crops worldwide, and rice plant diseases are a significant threat to global food security. Early detection and accurate classification of these diseases are crucial for effective disease management and prevention of crop losses. In this paper, we propose a novel computational intelligence-based technique for rice disease detection and classification. Our proposed method is composed of a residual network-based feature extractor followed by a Light Gradient Boosting Machine (LGBM) classifier. We use a publicly available rice leaf dataset to evaluate the performance of our proposed method. The results demonstrate that our proposed method achieves high accuracy, sensitivity, and specificity in identifying diseased rice plants, outperforming existing state-of-the-art methods. We also compare our proposed method against other methods using different performance metrics, showing its superior performance. The proposed method provides a promising approach to enhance rice crop health management and can be adapted and customized for other crops and agricultural settings. The proposed computational intelligence-based technique for rice disease detection and classification has significant implications for improving crop productivity and ensuring food security.