@article{article_1644650, title={Detection of Pine Processionary Moth (Thaumetopoea wilkinsoni) Nests Using Deep Learning}, journal={Black Sea Journal of Engineering and Science}, volume={8}, pages={1297–1306}, year={2025}, author={Gençtürk, Fatih and Isilak, Cemal and Üncü, İsmail Serkan}, keywords={Pine processionary moth, Deep learning, YOLOv7, Artificial intelligence, Forest pests, Classification}, 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.}, number={5}, publisher={Karyay Karadeniz Yayımcılık Ve Organizasyon Ticaret Limited Şirketi}