Cocoguard: A Comparative Study of YOLO-Family Models and Faster R-CNN for Coconut Pest Identification With Rule-Based Decision Support

Coconut farming is a vital component of the Philippine agricultural sector; however, destructive pests such as the Asiatic Palm Weevil, Rhinoceros Beetle, Brontispa beetle, and Slug Caterpillar can significantly reduce crop yields when infestations are not detected early. Conventional pest monitoring relies on manual inspection and delayed expert consultation, making pest identification slow and often inaccessible for smallholder farmers. This study proposes CocoGuard, a mobile-accessible artificial intelligence-assisted system for coconut pest detection using deep learning object detection models. A dataset of 2,076 coconut pest images, expanded to 5,398 images through augmentation, was prepared and annotated into seven pest classes. Several object detection models were benchmarked using Precision, Recall, F1-score, and mean Average Precision. Results show that YOLO26s achieved the best performance, obtaining 92.72% mAP@0.5, 92.51% precision, and 89.49% recall while maintaining computational efficiency suitable for mobile deployment.

Coconut Pest Detection, Image Processing

1. B. J. M. Almarinez et al., “Biological control: A major component of the pest management program for the invasive coconut scale insect Aspidiotus rigidus Reyne in the Philippines,” Insects, vol. 11, no. 11, p. 745, 2020. [Google Scholar] [Crossref]

2. Z.-J. Astoveza et al., “COCODY: Identifying coconut disease and pest infestation using CNN algorithm with simulation,” AIP Conf. Proc., vol. 3287, p. 030008, 2024. [Google Scholar] [Crossref]

3. C. M. Badgujar, A. Poulose, and H. Gan, “Agricultural object detection with YOLO algorithm: A bibliometric and systematic review,” arXiv preprint, 2024. [Google Scholar] [Crossref]

4. U. Barman, C. Pathak, and N. K. Mazumder, “Comparative assessment of pest damage identification of coconut plant,” Multimedia Tools Appl., vol. 82, pp. 25083–25105, 2023. [Google Scholar] [Crossref]

5. P. Christakakis et al., “Smartphone-based citizen science tool for plant disease and insect pest detection,” Technologies, vol. 12, no. 7, p. 101, 2024. [Google Scholar] [Crossref]

6. M. Daga, D. Parikh, and S. P. Ramu, “DeepSeqCoco: A mobile-friendly deep learning model for coconut disease detection,” in Proc. IEEE Conf., 2024. [Google Scholar] [Crossref]

7. M. E. A. Dumale et al., “Evaluation of biological control through AutoPPLeX in smart farming,” in DLSU Res. Congress Proc., 2022. [Google Scholar] [Crossref]

8. C. W. Fodulla, S. C. A. Manaig, and V. A. A. Gabin, “Design of a Raspberry Pi-based coconut pest detection system,” Preprint, 2023. [Google Scholar] [Crossref]

9. J. Frayco, “Digital technologies in plant disease and pest management,” 2025. [Google Scholar] [Crossref]

10. M. D. Gerance et al., “SaBaTech: A banana pest and disease detection web application,” Asian J. Data Sci. AI, 2023. [Google Scholar] [Crossref]

11. A. C. Guiam et al., “SPIDTECH: A mobile application for pest monitoring in the Philippines,” 2021. [Google Scholar] [Crossref]

12. M. L. A. Hosang et al., “Pest and disease challenges and control strategies for coconut,” IOP Conf. Ser. Earth Environ. Sci., vol. 1235, p. 012010, 2023. [Google Scholar] [Crossref]

13. M. E. Karar et al., “Mobile application for agricultural pest recognition using deep learning,” Ain Shams Eng. J., vol. 12, no. 4, pp. 3747–3756, 2021. [Google Scholar] [Crossref]

14. S. Khalid et al., “Small pest detection using deep learning object detection,” Sustainability, vol. 15, no. 8, p. 6815, 2023. [Google Scholar] [Crossref]

15. R. A. Latina et al., “PCR-based marker for detection of Aspidiotus rigidus,” J. Asia-Pacific Entomol., vol. 24, no. 4, pp. 873–881, 2021. [Google Scholar] [Crossref]

16. K.-R. Li et al., “Pest detection based on lightweight Faster R-CNN,” Agronomy, vol. 14, no. 10, p. 2303, 2024. [Google Scholar] [Crossref]

17. R. I. Marasigan et al., “CocoSense: Coconut tree detection using YOLOv7,” E3S Web Conf., vol. 488, p. 03015, 2024. [Google Scholar] [Crossref]

18. R. K. Megalingam et al., “Deep learning approach to identify pests in coconut trees,” in Proc. IEEE, 2024. [Google Scholar] [Crossref]

19. M. L. Moreno, J. K. M. Kuwornu, and S. Szabo, “Overview of the coconut supply chain in the Philippines,” J. Sustain. Dev., 2020. [Google Scholar] [Crossref]

20. A. A. Murat and M. S. Kiran, “A review on YOLO versions for object detection,” J. King Saud Univ. Comput. Inf. Sci., 2025. [Google Scholar] [Crossref]

21. PCAARRD, “Coconut,” 2023. [Online]. Available. [Google Scholar] [Crossref]

22. A. Redford et al., “Digital identification tools for plant biosecurity,” Plant Protection Quarterly, 2022. [Google Scholar] [Crossref]

23. J. Ricofuerto, “Coconut palm tree detection using deep learning,” 2025. [Google Scholar] [Crossref]

24. R. Sapkota et al., “YOLO26: Architectural enhancements for real-time detection,” arXiv preprint, 2025. [Google Scholar] [Crossref]

25. A. Sharma, V. Kumar, and L. Longchamps, “Comparative performance of YOLO and Faster R-CNN models,” Smart Agric. Technol., vol. 6, p. 100324, 2024 [Google Scholar] [Crossref]

26. Z. Wang, L. Qiao, and M. Wang, “Agricultural pest detection based on Faster R-CNN,” in Proc. SPIE, 2022. [Google Scholar] [Crossref]

• Breeding for a Greener Future: Selective Breeding and Crossbreeding Approaches to Minimize Methane Emissions in Ruminant Livestock
• Determinants of Adoption of Post-Harvest Losses Prevention Techniques among Banana/Plantain Marketers in Lagos State, Nigeria
• Enhancing Rice Yield Prediction Using UAV-Based Multispectral Imaging and Machine Learning Algorithms
• Seed-Borne Fungi of Groundnuts (Arachis Hypogaea) and Their Management with Ginger (Zingiber Officinale) Extract In Makurdi, Nigeria
• The Influence of Landforms and Slope on Agricultural Cropping Patterns in Chhatrapati Sambhajinagar District