Shuxin Xu

Mr. Shuxin Xu

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
JWJun Wu
Jun Wu
SXShuxin Xu
Shuxin Xu
LZLonghao Zhang
Longhao Zhang
PLPengbo Li
Pengbo Li
HWHaitao Wang
Haitao Wang
SZShengbei Zhou
Shengbei Zhou
The conflict between public health risks caused by allergenic tree species in urban greening and the goal of promoting urban ecological biodiversity has become a major challenge for allocating urban ecological resources. In March 2025, the “yellow haze incident” in the Temple of Heaven area in Beijing intensified this conflict and highlighted the problem of pollen allergenicity in urban plants, drawing wide attention to highly allergenic tree species used in urban landscaping. This paper proposes a tree species identification method that combines high-resolution satellite imagery with the YOLOv8s object detection model and focuses on Platycladus orientalis. Three lightweight modules, the Spatial Context-Aware Module (SCAM), the Feature Reconstruction Module (FRM), and the Bidirectional Feature Pyramid Network (BiFPN), are added to the neck of the baseline model to enhance its ability to identify Platycladus orientalis in remote sensing images. The enhanced YOLOv8s model achieves a precision of 81.39%, a recall of 78.70%, an mAP50 of 83.32%, and an F1 score of 80.81% for urban Platycladus orientalis detection. Using this model, we extract 118,723 Platycladus orientalis instances from sub-meter satellite remote sensing imagery of Beijing and generate a spatial distribution map. These results show that the enhanced YOLOv8 model can support the identification and analysis of the spatial distribution of the target tree species. The proposed method provides basic data and decision support for urban plant species identification, statistical analysis, and planning management.

28 March 2026 in Forests
Verified
Journal Article
Open access
PDF file
SXShuxin Xu
Shuxin Xu
SZShengbei Zhou
Shengbei Zhou
Jun WuJun Wu
Jun Wu
PLPengbo Li
Pengbo Li
With the continuous renewal of urban greening, pollen released by allergenic tree species has become a prominent environmental issue affecting residents’ health. However, existing research still lacks city-wide, rapidly replicable methods for identifying allergenic tree species and assessing exposure risks. Taking Beijing’s central urban districts as a case study, this research establishes a method for the automated identification of allergenic tree species and the assessment of pollen exposure risks based on high-resolution satellite imagery. This study coupled tree species distribution results derived from model inference with population density per unit area to delineate three tiers of exposure risk zones. Subsequently, these risk zones were overlaid with the road network within the study area to determine the distribution of roads with low, medium, and high exposure risk. Public transport stop locations were then introduced as a proxy variable for areas of high population mobility. Lorenz curves and Gini coefficients were calculated to quantify the spatial equity of pollen exposure risk. The results indicate that the model reliably identifies target tree species, with approximately 117,000 valid targets. Exposure risks exhibit significant clustering characteristics and can form continuous expansions along road networks. Incorporating population factors shows minimal change in risk concentration, suggesting pollen exposure risk is primarily driven by the spatial clustering of allergenic tree species and their accessibility within road networks. This risk is highly correlated with the spatial distribution patterns and accessibility characteristics of allergenic tree species, rather than being solely determined by population size. This study provides foundational data and methodological support for urban tree species identification, pollen exposure risk management, and optimised greening configurations.