YOLO for early detection and management of Tuta absoluta-induced tomato leaf diseases

• DOI: 10.3389/fpls.2025.1524630
• Publication Date: 2025-05-20T10:08:10Z
• Authors: Harisu Abdullahi ...; Aniebietabasi Ackley; Marvellous Mark; Ofem Ebriba Eteng; Md. Haidar Sharif; Huseyin Kusetogul...
• Keywords: Tuta absoluta

The agricultural sector faces persistent threats from plant diseases and pests, with Tuta absoluta posing a severe risk to tomato farming by causing up 100% crop loss. Timely pest detection is essential for effective intervention, yet traditional methods remain labor-intensive inefficient. Recent advancements in deep learning offer promising solutions, YOLOv8 emerging as leading real-time model due its speed accuracy, outperforming previous models on-field deployment. This study focuses on the early of absoluta-induced leaf Sub-Saharan Africa. first major contribution annotation dataset (TomatoEbola), which consists 326 images 784 annotations collected three different farms now publicly available. second key proposal transfer learning-based approach evaluate YOLOv8's performance detecting absoluta. Experimental results highlight model's effectiveness, mean average precision 0.737, other state-of-the-art that achieve less than 0.69, demonstrating capability real-world These findings suggest AI-driven solutions like could play pivotal role reducing losses enhancing food security.