Xiaolong Pei

Mr. Xiaolong Pei

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
31 October 2024 in Forests
Verified
Journal Article
Open access
PDF file
LMLei Mao
Lei Mao
XPXiaolong Pei
Xiaolong Pei
CHChunhui He
Chunhui He
PBPeng Bian
Peng Bian
DSDongyang Song
Dongyang Song
GTGuanghao Tian Tian
Guanghao Tian Tian
As global climate change intensifies, arid land ecosystems face increasing challenges. Vegetation, a key indicator of climate variation, is highly responsive to meteorological factors such as temperature (Tem), precipitation (Pre), and soil moisture (SM). Understanding how fractional vegetation cover (FVC) responds to climate change in arid regions is critical for mitigating its impacts. This study utilizes MOD13Q1-NDVI data from 2000 to 2022, alongside corresponding Tem, Pre, and SM data, to explore the dynamics and underlying mechanisms of SM and FVC in the context of climate change. The results reveal that both climate change and human activities exacerbate vegetation degradation, underscoring its vulnerability. A strong correlation between FVC and both Tem and Pre suggests that these factors significantly influence FVC variability. In conclusion, FVC in the lower reaches of the Heihe River is shaped by a complex interplay of Tem, Pre, SM, and human activities. The findings provide a scientific basis and decision-making support for ecological conservation and water resource management in the lower reaches of the Heihe River, aiding in the development of more effective strategies to address future climate challenges.

10 October 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
BXBo Xu
Bo Xu
DCDi Cai
Di Cai
KSKelin Sui
Kelin Sui
ZWZheng Wang
Zheng Wang
CLChuangchuang Liu
Chuangchuang Liu
XPXiaolong Pei
Xiaolong Pei
To address the challenges of low detection accuracy and weak generalization in UAV aerial imagery caused by complex ground environments, significant scale variations among targets, dense small objects, and background interference, this paper proposes an improved lightweight multi-scale small-object detection model, MBD-YOLO (MBFF module, BiMS-FPN, and Dual-Stream Head). Specifically, to enhance multi-scale feature extraction capabilities, we introduce the Multi-Branch Feature Fusion (MBFF) module, which dynamically adjusts receptive fields through parallel branches and adaptive depthwise convolutions, expanding the receptive field while preserving detail perception. We further design a lightweight Bidirectional Multi-Scale Feature Aggregation Pyramid Network (BiMS-FPN), integrating bidirectional propagation paths and a Multi-Scale Feature Aggregation (MSFA) module to mitigate feature spatial misalignment and improve small-target detection. Additionally, the Dual-Stream Head with NMS-free architecture leverages a task-aligned architecture and dynamic matching strategies to boost inference speed without compromising accuracy. Experiments on the VisDrone2019 dataset demonstrate that MBD-YOLO-n surpasses YOLOv8n by 6.3% in mAP50 and 8.2% in mAP50–95, with accuracy gains of 17.96–55.56% for several small-target categories, while increasing parameters by merely 3.1%. Moreover, MBD-YOLO-s achieves superior detection accuracy, efficiency, and generalization with only 12.1 million parameters, outperforming state-of-the-art models and proving suitable for resource-constrained embedded deployment scenarios. The superior performance of MBD-YOLO, which harmonizes high precision with low computational demand, fulfills the critical requirements for real-time deployment on resource-limited UAVs, showing great promise for applications in traffic monitoring, urban security, and agricultural surveying.

18 November 2024 in Forests
Verified
Journal Article
Open access
PDF file
DSDongyang Song
Dongyang Song
XPXiaolong Pei
Xiaolong Pei
LMLei Mao
Lei Mao
JWJiangyulong Wang
Jiangyulong Wang
YTYe Tian
Ye Tian
HAHongyan An
Hongyan An
Ejina, a representative inland river basin situated in the arid region of northwest China, exhibits a delicate ecological environment and its vegetation coverage is intrinsically linked to regional ecological security. Based on MOD13Q1-NDVI data from 2018 to 2023 and groundwater depth monitoring data during the same period, this study analyzed the spatial–temporal variation characteristics of vegetation coverage and its relationship with groundwater depth in Ejina. It is found that the vegetation coverage in Ejina is generally low and mainly distributed along the riverbanks in the form of strips. During the study period, the overall trend of vegetation coverage showed a fluctuating pattern of first increasing and then decreasing, revealing the fragility of the regional ecology. The groundwater depth shows the characteristic of being higher in the east river than the west, and the trend of groundwater depth along the river flow is first increasing and then decreasing. The spatial groundwater depth indicates that the east river is higher than that of the west river, and the groundwater depth along the river flow first increases and then decreases. In terms of inter-annual changes, the groundwater depth experiences a process of first decreasing and then stabilizing. Further analysis indicates that vegetation growth and coverage in Ejina are significantly affected by water conditions, and areas with high Normalized Difference Vegetation Index (NDVI) values are mainly distributed along the riverbanks. In addition, there is a certain degree of correlation between groundwater depth and NDVI. When the depth of groundwater is too deep or too shallow, the positive correlation between NDVI and groundwater depth increases slightly and the negative correlation decreases slightly. The findings of this study are of great significance for understanding and predicting the response of vegetation coverage to groundwater changes in arid areas, and provide a scientific basis for water resources management and ecological protection in Ejina.