YOLOv11n-Based Oil Palm Health Classification Using Orthomosaic Drone Imagery

Maudy Hellena Harlyn (Department of Information Systems and Technology, Faculty of Science and Technology, Institut Teknologi Sawit Indonesia, Medan, North Sumatra, Indonesia)
Ritna Wahyuni (Department of Information Systems and Technology, Faculty of Science and Technology, Institut Teknologi Sawit Indonesia, Medan, North Sumatra, Indonesia)
Andi Prayogi (Department of Information Systems and Technology, Faculty of Science and Technology, Institut Teknologi Sawit Indonesia, Medan, North Sumatra, Indonesia)

Teknika
Vol. 15 No. 2 (2026): July 2026

Monitoring oil palm plantation conditions across large-scale areas remains challenging because manual inspection is time-consuming, costly, and prone to observational errors. This study aims to develop a GIS-based monitoring system for oil palm health detection using the YOLOv11n algorithm and orthomosaic imagery acquired from UAV mapping. The study employed the Software Development Life Cycle (SDLC) Waterfall model and Unified Modeling Language (UML) for system development and design. The research stages included orthomosaic image acquisition, image tiling, dataset annotation, data augmentation, YOLOv11n model training, system implementation, and functional testing. The dataset was collected from oil palm plantation areas owned by PT Bakrie Sumatera Plantations and classified into three categories: healthy, unhealthy, and dead trees. The evaluation results demonstrated high detection performance with 0.99 precision, 0.99 recall, 0.99 mAP50, and 0.88 mAP50-95. The developed GEOPALM system was capable of generating centroid-based visualizations, plantation condition distribution graphs, and spatial outputs for plantation monitoring purposes. Overall, the proposed system can support faster, more efficient, and spatially structured oil palm plantation monitoring.