This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
YOLO-PTHD: A UAV-Based Deep Learning Model for Detecting Visible Phenotypic Signs of Pine Decline Induced by the Invasive Woodwasp Sirex noctilio (Hymenoptera, Siricidae)
by
Wenshuo Yang
1,2, 
Jiaqiang Zhao
3,
Dexu Zhu
1,2,
Zhengtong Wang
1,2,
Min Song
4,
Tao Chen
5,
Te Liang
1,2 and
Juan Shi
1,2,* 1
Beijing Key Laboratory for Forest Pest Control, Beijing Forestry University, Beijing 100083, China
2
Sino-French Joint Laboratory for Invasive Forest Pests in Eurasia, Beijing Forestry University, Beijing 100083, China
3
Shijiazhuang Institute of Fruit Trees, Hebei Academy of Agriculture and Forestry Sciences, Shijiazhuang 050061, China
4
Heilongjiang Provincial Station for Forest Pest and Disease Control and Quarantine, Harbin 140080, China
5
Fujin City Forest Pest and Disease Control and Quarantine Station, Jiamusi 146100, China
*
Author to whom correspondence should be addressed.
Insects 2025, 16(8), 829; https://doi.org/10.3390/insects16080829 (registering DOI)
Submission received: 14 July 2025
/
Revised: 5 August 2025
/
Accepted: 7 August 2025
/
Published: 9 August 2025
(This article belongs to the Special Issue Surveillance and Management of Invasive Insects)
Simple Summary
Pine trees are vital for forests and the environment, but they are increasingly threatened by an invasive insect called the Sirex noctilio. This pest weakens and kills trees, often without obvious early signs. Traditional inspection methods are slow and may miss early damage. In this study, we created a new method that uses UAVs and artificial intelligence to quickly find unhealthy pine trees by analyzing aerial images. Our approach can detect changes in needle color and tree shape, even in partially occluded scenes. We tested the method on real forest images and confirmed its accuracy through ground surveys. It worked well in different locations and with other tree diseases too. This technology offers a fast, accurate, and practical way to monitor forest health and could help prevent large-scale tree losses.
Abstract
Sirex noctilio is an invasive pest that contributes to pine tree decline, leading to visual symptoms such as needle discoloration, crown thinning, and eventual tree death. Detecting these visible phenotypic signs from drone imagery is challenging due to elongated or irregular crown shapes, weak color differences, and occlusion within dense forests. This study introduces YOLO-PTHD, a lightweight deep learning model designed for detecting visible signs of pine decline in UAV images. The model integrates three customized components: Strip-based convolution to capture elongated tree structures, Channel-Aware Attention to enhance weak visual cues, and a scale-sensitive dynamic loss function to improve detection of minority classes and small targets. A UAV-based dataset, the Sirex Woodwasp dataset, was constructed with annotated images of weakened, and dead pine trees. YOLO-PTHD achieved an mAP of 0.923 and an F1-score of 0.866 on this dataset. To evaluate the model’s generalization capability, it was further tested on the Real Pine Wilt Disease dataset from South Korea. Despite differences in tree symptoms and imaging conditions, the model maintained strong performance, demonstrating its robustness across different forest health scenarios. Field investigations targeting Sirex woodwasp in outbreak areas confirmed that the model could reliably detect damaged trees in real-world forest environments. This work demonstrates the potential of UAV-based visual analysis for large-scale phenotypic surveillance of pine health in forest management.
Keywords:
invasive species; Sirex noctilio; deep learning; YOLO; UAV image; pine tree; object detection
