Bochuan Zhou

Mr. Bochuan Zhou


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
18 March 2025 in Land
Verified
Journal Article
Open access
PDF file
ZZZhen Zhong
Zhen Zhong
BZBochuan Zhou
Bochuan Zhou
LKLingqiang Kong
Lingqiang Kong
XFXUENING FANG
XUENING FANG
Sustainable landscape management requires accurately identifying the trade-offs and synergies among ecosystem services (ES). Three commonly utilized approaches to quantify ES trade-off/synergy relationships include the space-for-time approach, landscape background-adjusted space-for-time approach, and temporal trend approach. However, the similarities and differences among these three approaches in identifying ES relationships in the same area remain unclear. Thus, we conducted a case study in the rapidly urbanizing Yangtze River Delta region, comparing the three approaches based on annual data spanning from 2001 to 2020 for 12 types of ES. We found that: (1) the ES trade-off/synergy relationships detected by the three approaches exhibit significant divergence, with only 1.45% consistency among the 66 pairs of ES relationships. (2) All three approaches can overlook ES trade-offs, miss ES synergies, and erroneously detect interactions where none exist. (3) The mechanisms contributing to the misidentification of ES relationships by the three approaches include: neglecting the underlying assumptions of different approaches, insufficient time interval length, short time series of ES data, data aggregation effects, non-linear changes in ESs, time lag effects of ES relationships, among others. Our results indicate that each of the three approaches has its own advantages and disadvantages in identifying ES relationships. Prior to selecting an approach for identifying relationships between ESs in a specific study area, careful consideration of the availability of time series data, the characteristics of the chosen ES type, and thorough examination of the underlying assumptions and uncertainties of each approach are imperative.

26 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
ZZZhi Zheng
Zhi Zheng
BZBochuan Zhou
Bochuan Zhou
Yuping SongYuping Song
Yuping Song
Cryptocurrency transaction fraud detection faces the dual challenges of increasingly complex transaction patterns and severe class imbalance. Traditional methods rely on manual feature engineering and struggle to capture temporal and structural dependencies in transaction networks. This paper proposes an Augmented Temporal-aware Graph Attention Network (ATGAT) that enhances detection performance through three modules: (1) designing an advanced temporal embedding module that fuses multi-scale time difference features with periodic position encoding; (2) constructing a temporal-aware triple attention mechanism that jointly optimizes structural, temporal, and global context attention; (3) employing weighted BCE loss to address class imbalance. Experiments on the Elliptic++ cryptocurrency dataset demonstrate that ATGAT achieves an AUC of 0.9130, representing a 9.2% improvement over the best traditional method XGBoost, 12.0% over GCN, and 10.0% over standard GAT. This method not only validates the enhancement effect of temporal awareness and triple attention mechanisms on graph neural networks, but also provides financial institutions with more reliable fraud detection tools, with its design principles generalizable to other temporal graph anomaly detection tasks.

30 June 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
LSLIN SHAO
LIN SHAO
BZBochuan Zhou
Bochuan Zhou
YLYeyang Li
Yeyang Li
QHQiaoli Huang
Qiaoli Huang
XFXUENING FANG
XUENING FANG
Rural areas are experiencing significant changes in socio-economic and spatial patterns, and research on the characteristics of rural restructuring is conducive to the planning of rural revitalization. However, few studies have focused on the changes in regional development imbalances in the process of rural restructuring. This study aims to explore whether rural restructuring mitigates or exacerbates existing regional disparities, and to assess the degree of coordination among economic, social, and spatial restructuring dimensions. In this study, the evolution of spatio-temporal patterns and divergence characteristics of unevenly developed regions in the process of rural restructuring from 2010 to 2020 were investigated by using the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) model and the coupled coordination model. We found the following: (1) The level of rural development has increased significantly and the overall pattern has not changed. Meanwhile, the degree of regional imbalance has deepened, evolving from a low level of disequilibrium to a pattern of high levels but more pronounced spatial polarization. (2) The impacts of different dimensions of rural restructuring on regional imbalance are not consistent, and the social and spatial dimensions are significantly more unbalanced than the economic dimension. (3) The analysis of the driving mechanism shows that there are significant spatial and temporal differences between a variety of driving factors, the strength of their role, positive and negative have evolved in stages, and the transition from a government-led to a market-driven trend is gradually obvious. In the future, rural planning should pay more attention to resource inputs in the social and spatial dimensions, and improve the equilibrium of the social and spatial dimensions, which is more conducive to mitigating the trend of regional polarization.