Advancing disease identification in fava bean crops: A novel deep learning solution integrating YOLO-NAS for precise rust

Abstract

 A significant concern is the economic impact of agricultural diseases on the world’s crop production. The disease significantly reduces agricultural production across the world. Loss of nutrients caused by parasite infection of leaves, pods, and roots–the pathogenic agent that causes fava bean rust disease–decreases crop health. This work addresses this requirement by offering an innovative deep-learning model approach for early identification and classification of fava bean rust disease. The suggested method uses the effectiveness of modern YOLO-based object detection architectures like You Only Look Once –Neural Architecture Search (YOLO-NAS) L, YOLO-NASM, and YOLO-NASS, Faster Region-based Convolutional Neural Network (Faster R-CNN), and RetinaNet. An inclusive dataset of 3296 images of various lighting and background situations was selected for extensive model training. Each model underwent thorough training and adjusted parameters through careful experimentation. The models’ comparative studies found significant performance differences. The precision for YOLO-NASL was 82.10% ; for YOLO-NASM, it was 84.80% ; for YOLO-NASS, it was 83.90% ; for Faster R-CNN, it was 75.51% ; and for RetinaNet, it was 73.74% . According to the evaluation, model complexity and detection accuracy are directly correlated. YOLO-NASL, YOLO-NASM, and YOLO-NASS showed remarkable mean average precision values of 90.90%, 94.10%, and 92.60%, respectively, and became highly functional models. The fastest model was YOLO-NASS. Its satisfying recognition speed made real-time detection possible in particular applications. The YOLO-NASM model, which shows an extraordinary state-of-the-art performance, represents the pinnacle of our work. Its mean average precision (mAP@0.5) was 94.10%, with notable values of 90.84%, 96.96%, and 84.80% for the F1-score, Recall, and precision, respectively. This investigation addresses a critical need in agricultural disease management, aligning with broader global efforts toward sustainable agriculture. Our studies add to the knowledge about precision agriculture and inspire practical, long-lasting disease management techniques in the agricultural industry. The real-time performance of the system will need to be improved, and satellite imagery integration may be considered in the future to provide more comprehensive coverage.