Detection of Pine Processionary Moth (Thaumetopoea wilkinsoni) Nests Using Deep Learning

Abstract

The pine processionary moth, widely found in Southern and Central Europe, North Africa, and the Middle East, causes significant economic and ecological losses in forests. This pest feeds on the needles of pine species, posing a greater threat than forest fires in Türkiye, where a large portion of the timber resource is made up of pine trees. This study aims to detect nests of the pine processionary moth residing on trees. A custom dataset was created using aerial images of infested pine trees. A deep learning model was trained using this dataset to facilitate nest detection. Using the YOLOv7 network, training and testing were performed on two datasets of different sizes. The analysis revealed that the dataset with a larger number of images yielded better performance in detecting pine processionary moth nests. The detection success of the model for nests was measured as 92.5% based on the mAP@0.5 metric. The findings of this study demonstrate the effectiveness of the proposed method for accurate and high-resolution detection of pine processionary moth nests in forestry applications. Moreover, these findings highlight the method’s potential to support pest density monitoring and the identification of intervention priority areas. Future research should investigate the applicability of the proposed approach to other pest species and explore its integration into real-time monitoring and pest management systems for large-scale operations.

Keywords

• Pine processionary moth
• Deep learning
• YOLOv7
• Artificial intelligence
• Forest pests
• Classification

References

1. Akıncı Ş, Göktoğan AH. 2022. An Eco-Friendly Fight Against Thaumetopoea Pityocampa Infestations in Pine Forests Using Deep Learning on UAV Imagery. IEEE, In 2022 Innovations in Intelligent Systems and Applications Conference (ASYU), pp: 1-6.
2. Ali ML, Zhang Z. 2024. The YOLO framework: A comprehensive review of evolution, applications, and benchmarks in object detection. Computers, 13: 336.
3. Anonymous. 2016. Orman Bitkisi ve Bitkisel Ürünlerine Arız Olan Zararlı Organizmalar ile Mücadele Yöntemleri. URL: https://www.ogm.gov.tr/tr/e-kutuphane-sitesi/EgitimDokumanlari/Orman%20Zararl%C4%B1lar%C4%B1yla%20M%C3%BCcadele/Orman%20Bitkisi%20ve%20Bitkisel%20%C3%9Cr%C3%BCnlerine%20Ar%C4%B1z%20Olan%20Zararl%C4%B1%20Organizmalar%20ile%20M%C3%BCcadele%20Y%C3%B6ntemleri.pdf. (accessed date: January 14, 2025).
4. Anonymous. 2017. Google Colab. URL: https://colab.research.google.com (accessed date: February 09, 2024).
5. Anonymous. 2022. Get started now. URL: makesense.io (accessed date: January 12, 2025).
6. Arnaldo PS, Chacim S, Lopes D. 2010. Effects of defoliation by the pine processionary moth Thaumetopoea pityocampa on biomass growth of young stands of Pinus pinaster in northern Portugal. iForest, 3:159.
7. Avcı M, Altunışık A. 2016. Isparta çam ormanlarında çam kese böceği (Thaumetopoea wilkinsoni Tams, 1926) (Lep.: Notodontidae) zararının artım üzerine etkisi. Türkiye Entomoloji Bülteni, 6:231-244.
8. Babur H. 2002. Thaumetopoea Pityocampa (Schiff.) Çam Gençliğinde Zarar Miktarı. Ülkemiz Ormanlarında Çam Keseböceği Sorunu ve Çözüm Önerileri Sempozyumu April 24-25, Kahramanmaraş, pp: 37-43.

9. Çanakçıoğlu H. 1993. Orman Entomolojisi, İstanbul Üniversitesi Orman Fakültesi Yayınları. (pp: 29-36).
10. Cardil A, Otsu K, Pla M, Silva CA, Brotons L. 2019. Quantifying pine processionary moth defoliation in a pine-oak mixed forest using unmanned aerial systems and multispectral imagery. Plos One, 14: e0213027.
11. Cardil A, Vepakomma U, Brotons L. 2017. Assessing pine processionary moth defoliation using unmanned aerial systems. Forests, 8:, 402.
12. Carus S. 2004. Impact of defoliation by the pine processionary moth (Thaumetopoea pityocampa) on radial, height and volume growth of calabrian pine (Pinus brutia) trees in Türkiye. Phytoparasitica, 32: 459-469.
13. Cebeci HH, Oymen RT, Acer S. 2010. Control of pine processionary moth, Thaumetopoea pityocampa with Bacillus thuringiensis in Antalya, Türkiye. J Environ Biol, 31: 357-361.
14. Chen CJ, Huang YY, Li YS, Chen YC, Chang CY, Huang YM. 2021. Identification of fruit tree pests with deep learning on embedded drone to achieve accurate pesticide spraying. IEEE Access, 9:21986-21997.
15. Erkan N. 2011. Impact of pine processionary moth (Thaumetopoea wilkinsoni Tams) on growth of Turkish red pine (Pinus brutia Ten.). Afr J Agric Res, 6: 4983-4988.
16. Gooshbor L, Bavaghar MP, Amanollahi J, Ghobari H. 2016. Monitoring infestations of oak forests by Tortrix viridana (Lepidoptera: Tortricidae) using remote sensing. Plant Prot Sci, 52: 270-276.
17. Işilak C, Durmaz O, Şalk Y, Çevılkalp H, Dutağaci H, Gırgın T. 2023. Measuring Electromagnetic Field Strength in Base Stations Using Unmanned Aerial Vehicles. In 2023 31st Signal Processing and Communications Applications Conference (SIU) (pp: 1-4). IEEE.
18. Kerkech M, Hafiane A, Canals R. 2020. Vine disease detection in UAV multispectral images using optimized image registration and deep learning segmentation approach. Comput Electron Agric, 174:105446.
19. Nguyen HV, Bae JH, Lee YE, Lee HS, Kwon KR. 2022. Comparison of pre-trained yolo models on steel surface defects detector based on transfer learning with gpu-based embedded devices. Sensors, 22:9926.
20. Özay FŞ. 2004. Çam keseböceği (Thaumetopoea pityocampa Schiff.) (Lepidoptera-Thaumetopoeidae) ve mücadele yöntemleri. Kavak ve Hızlı Gelişen Orman Ağaçları Araşt. Enst. Müd. Kavakçılık Araştırma Dergisi, 30:55-65.
21. Özcan GE, Sivrikaya F. 2022. Determining Infestation of Pine Processionary Moth Using Remote Sensing. 4th Intercontinental Geoinformation Days, June 20-21, Tabriz, pp: 99-102.
22. Özdal MH. 2002. Çam Keseböceği ile Adacıklarla Mücadele Yöntemi, Ülkemiz Ormanlarında Çam Keseböceği Sorunu ve Çözüm Önerileri Sempozyumu Bildiri Kitabı, Kahramanmaraş, pp: 226.
23. Padilla R, Netto SL, Da Silva EA. 2020. A survey on performance metrics for object-detection algorithms. In 2020 international conference on systems, signals and image processing (IWSSIP). IEEE, pp: 237-242.
24. Redmon J, Divvala S, Girshick R, Farhadi A. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition. pp: 779- 788.
25. Terven J, Córdova-Esparza DM, Romero-González JA. 2023. A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas. Mach Learn Knowl Extr, 5: 1680-1716.
26. Wang C-Y, Bochkovskiy A, Liao HYM. 2022. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv. http://arxiv.org/abs/2207.02696.
27. Yüksel H. 2019. Investigation of the relationship between altitude and biological and ecological characteristics of egg and egg batch in thaumetopoea wilkinsoni tams, 1924 and thaumetopoea pityocampa (den. & schiff., 1775) (lepidoptera: notodontidae) populations. Master's Thesis, Bartın University, Institute of Science, Bartın, pp:59.
28. Ziya A, Mehmet MO, Yusuf Y. 2018. Determination of Sugar Beet Leaf Spot Disease Level (Cercospora beticola Sacc.) with Image Processing Technique by Using Drone. Curr Inves Agri Curr Res 5 (3)-2018. Mediterranea, 34(3): 149-156.
29. Zhang Z, Xie X, Guo Q, Xu J. 2024. Improved YOLOv7-Tiny for object detection based on UAV aerial images. Electronics, 13(15): 2969.