Multiple Rice Leaf Disease Prediction for MO4 Rice Leaf Variety in Dakshina Kannada Using Deep Learning Technique

Abstract

Rice serves as a staple food for millions worldwide, yet its productivity and quality are often compromised by diseases. This challenge is particularly evident in Dakshina Kannada, Karnataka, a region renowned for cultivating the MO4 rice variety. MO4 rice is especially susceptible to diseases like bacterial leaf blight, sheath blight, and neck blast, which can lead to significant crop losses if not addressed promptly. Early and accurate disease detection is critical for effective management strategies and ensuring agricultural sustainability.[3] To tackle this issue, we propose a deep learning-based system that leverages convolutional neural networks (CNNs) for the detection and classification of rice leaf diseases. Our study involved compiling an extensive and meticulously annotated dataset of MO4 rice leaf images, representing both healthy and diseased samples.

The CNN model was fine-tuned to achieve high accuracy, precision, recall, and F1 scores, demonstrating its effectiveness in disease detection. Rigorous testing under diverse conditions ensures the model's robustness and suitability for real-world applications. This system offers a practical tool for farmers and agricultural officers, enabling early diagnosis and timely intervention. By facilitating proactive disease management, it helps reduce crop losses, improve productivity, and support sustainable agriculture. Our experimental results underscore the potential of this deep learning-based approach to revolutionize rice disease management, particularly in Dakshina Kannada. The proposed system contributes to the broader vision of intelligent agriculture, enhancing food security and empowering farmers with advanced technological tools.[1]