Abstract: Rice is a staple crop that plays a crucial role in global food security. However, its productivity is significantly affected by various diseases such as Bacterial Blight (BB), Brown Spot (BS), and Leaf Smut (LS). Early detection and classification of these diseases are essential for effective management and yield improvement. This paper presents an automated approach to rice plant disease detection using Neural Architecture Search (NAS), which optimizes convolutional neural network (CNN) architectures for high-accuracy classification. The system is trained on the Rice Life Disease Dataset, which contains extensive image data of diseased rice plants. NAS automates the model selection process, eliminating the need for manual experimentation while enhancing classification performance. The proposed model is evaluated using accuracy, precision, recall, and F1-score, demonstrating its effectiveness in disease identification. By integrating deep learning with automated model optimization, this research contributes to agricultural sustainability by providing farmers and agronomists with a reliable tool for early disease detection, thus reducing crop losses and improving productivity.

Keywords: Rice Plant Disease, Neural Architecture Search (NAS), Convolutional Neural Network (CNN), Bacterial Blight (BB), Deep Learning, Image Classification, Crop Monitoring.

| DOI: 10.17148/IARJSET.2025.12303