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.

Phoracantha recurva Newman (Coleoptera: Cerambycidae), a wood-boring beetle native to Australia, threatens Eucalyptus L’Hér plantations worldwide. Despite established populations across North America, South America, Europe, and Africa, its global colonization potential and niche dynamics under climate change have received limited attention. Here, we used the maximum entropy (MaxEnt) model, integrating 844 occurrence records and eight bioclimatic variables, to predict the potential geographical distribution of P. recurva under current conditions and three future climate scenarios (SSP1-2.6, SSP3-7.0, and SSP5-8.5) for 2041–2070 and 2071–2100. We quantified niche dynamics using the COUE framework through calculations of niche stability, expansion, unfilling, and Schoener’s D, complemented by niche equivalency and similarity tests. The model exhibited excellent predictive performance (AUC = 0.954 ± 0.004; Boyce index = 0.999). Suitable habitats for P. recurva occurred primarily between 60° N and 55° S. Under all three future scenarios, total suitable area displayed a gradual decline while the potential distribution shifted toward higher latitudes, particularly across Europe and China. Niche analysis confirmed substantial niche conservatism during global invasion, yet revealed considerable niche unfilling during colonization of the Eurasian continent—indicating persistent potential for further range expansion. Niche comparisons between native and invaded ranges under model-projected distributions yielded expanded overlap across all regions except Africa, where invasive populations may undergo niche differentiation under changing climatic conditions. Our findings emphasize the ongoing invasion risk that P. recurva poses to major Eucalyptus-planting countries and call for strengthened inspection and quarantine measures to protect global forestry plantations.

Pissodes castaneus is an internationally quarantined pest that damages various pine species. The global distribution patterns and invasion potential of P. castaneus have not been systematically assessed, thus leaving relevant prevention and control systems without a theoretical foundation. In this study, we used an optimized MaxEnt model to predict the global suitable areas of P. castaneus under current and future climate conditions. At the same time, it assesses the changes in the ecological niche of P. castaneus under climate change. The results indicate that the AUC values of the MaxEnt model exceeded 0.9 under both current and future climate scenarios, indicating high predictive accuracy. Under current climate conditions, the total global potential suitable area for P. castaneus is 1.08 × 10⁷ km². The highly suitable areas are mainly distributed in Western Europe, northern Turkey, southeastern Australia, the west coast of North America, and the east coast of South America. Under the two future climate scenarios (SSP126 and SSP585), the total suitable area initially decreases and then increases, reaching its maximum during 2081–2100. Compared with current conditions, suitable areas shift northward in the Northern Hemisphere. Under both the SSP126 and SSP585 scenarios, although its niche remains highly conservative relative to current conditions, different emission scenarios may affect the niche dynamics of P. castaneus. This study reveals the spatiotemporal dynamics of suitable areas and niche characteristics of P. castaneus on a global scale, providing a basis for worldwide quarantine and inspection efforts and offering scientific data support for future prevention and control of its spread.