Xiujuan He

Xiujuan He

Auto-generated profile, based on publicly available information

Xiujuan He

Department of Geography, The University of Hong Kong, Hong Kong, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
1 July 2024 in Journal of Environmental Management
Verified
Journal Article
Closed access
LZLilei ZHOU
Lilei ZHOU
MLMengyu Li
Mengyu Li
DGDongjie Guan
Dongjie Guan
STShuixian Tan
Shuixian Tan
CWCaihong Wang
Caihong Wang
XHXiujuan He
Xiujuan He

15 February 2023 in Buildings
Verified
Journal Article
Open access
PDF file
YQYansu Qi
Yansu Qi
XLXuefei Li
Xuefei Li
YLYingjie Liu
Yingjie Liu
XHXiujuan He
Xiujuan He
WGWeijun Gao
Weijun Gao
SMSheng Miao
Sheng Miao
Morphological indicators, which are important for urban planning, can be adjusted to effectively mitigate the heat island effect and promote a more comfortable urban environment. Most studies obtain the relationship between morphological indicators and land surface temperature (LST) from the urban scale, and it is difficult to apply the results to urban management and construction projects. Traditional research methods have ignored the complex and interactive relationship between morphological indicators and LST. In this work, the feed-forward neural network (FNN) model is utilized to model the nonlinear relationship between morphological indicators and LST at the block scale. After validation and comparison, the FNN model achieved MAE of 0.885 and RMSE of 1.184, indicating that the influence of morphological indicators on LST could be precisely mapped. In addition, using cooling LST as the optimization target, the specific indicator scheme is suggested based on the FNN model, where the percentage of green space is 17.1%, the percentage of impervious surface is 82.9%, the percentage of water is 0, the bare soil percentage is 0, the floor area ratio is 0.814, the building cover percentage is 32.2%, and the average building height is 7.2 m.

10 July 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
DGDongjie Guan
Dongjie Guan
YSYitong Shi
Yitong Shi
LZLilei ZHOU
Lilei ZHOU
XZXusen Zhu
Xusen Zhu
DZDemei Zhao
Demei Zhao
XHXiujuan He
Xiujuan He
Accurate forecasting of carbon emissions at the county level is critical to support China’s dual-carbon goals. However, most current studies are limited to national or provincial scales, employing traditional statistical methods inadequate for capturing complex nonlinear interactions and spatiotemporal dynamics at finer resolutions. To overcome these limitations, this study develops and validates a high-resolution predictive model using advanced gradient boosting algorithms—Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM)—based on socioeconomic, industrial, and environmental data from 2732 Chinese counties during 2008–2017. Key variables were selected through correlation analysis, missing values were interpolated using K-means clustering, and model parameters were systematically optimized via grid search and cross-validation. Among the algorithms tested, LightGBM achieved the best performance (R2 = 0.992, RMSE = 0.297), demonstrating both robustness and efficiency. Spatial–temporal analyses revealed that while national emissions are slowing, the eastern region is approaching stabilization, whereas emissions in central and western regions are projected to continue rising through 2027. Furthermore, SHapley Additive exPlanations (SHAP) were applied to interpret the marginal and interaction effects of key variables. The results indicate that GDP, energy intensity, and nighttime lights exert the greatest influence on model predictions, while ecological indicators such as NDVI exhibit negative associations. SHAP dependence plots further reveal nonlinear relationships and regional heterogeneity among factors. The key innovation of this study lies in constructing a scalable and interpretable county-level carbon emissions model that integrates gradient boosting with SHAP-based variable attribution, overcoming limitations in spatial resolution and model transparency.

YZYuxiang Zhang
Yuxiang Zhang
DGDongjie Guan
Dongjie Guan
XHXiujuan He
Xiujuan He
BYBoling Yin
Boling Yin
Urban sprawl has become the main pattern of spatial expansion in many large cities in China, and its ecological and environmental effects profoundly impact Chinese urban development. In this paper, nighttime light data and statistical yearbook data are adopted as basic data sources to simulate the evolution trend of the urban sprawl in the upper Yangtze River (UYR), China. First, the urban sprawl index (USI) is employed to assess the level of urban sprawl and to determine the characteristics of urban sprawl under different scales. Second, the spatial autocorrelation model is applied to reveal the spatial pattern change characteristics of urban sprawl from 1992 to 2015. Third, a scenario analysis model of urban sprawl is constructed to simulate the evolution trend of the urban sprawl under different scenarios. Finally, based on the Geodetector, the influence of factors and factor interactions influencing urban sprawl in different time periods is analyzed. The results yield the following main conclusions: (1) The urban sprawl in the UYR first intensifies and then stabilizes over time. The number of cities with high USI in Sichuan province, medium cities, and Chengdu-Chongqing urban agglomeration increases over time, indicating that urban sprawl is intensifying in these areas. (2) The urban sprawl hot spots experience a pattern transformation process of point-like expansion-point-ring expansion-point-axis expansion-axis radiation. (3) Under the scenarios with different scales, the urban land sprawl in large cities is the highest, accounting for more than 47% of the UYR. Urban land sprawl extent in the Chengdu-Chongqing urban agglomeration is the highest, accounting for more than 51% of the UYR. The cities exhibiting the highest sprawl are Chongqing, Lijiang, and Kunming, accounting for 25.84%, 7.37%, and 5.11%, respectively, of the UYR. (4) In the different time scenario simulations, the urban land in large cities exhibits the highest sprawl, accounting for approximately 48.16% of the UYR. The urban land in the Chengdu-Chongqing urban agglomeration demonstrates the highest sprawl, accounting for 50.92% of the UYR. (5) From 1996 to 2002, the driver with the highest influence on urban sprawl was secondary industry share of GDP, with a q-statistic of 0.616. From 2009 to 2015, the driver with the highest influence on urban sprawl was green space per capita with a q-statistic of 0.396.

22 December 2025 in Water Resources Management
Verified
Journal Article
Closed access
PDF file
DGDongjie Guan
Dongjie Guan
JCJiameng Cao
Jiameng Cao
XFXiaofeng Fan
Xiaofeng Fan
LZLilei ZHOU
Lilei ZHOU
XHXiujuan He
Xiujuan He
Kang-wen ZHUKang-wen ZHU
Kang-wen ZHU

3 January 2026 in Applied Water Science
Verified
Journal Article
Open access
PDF file
DGDongjie Guan
Dongjie Guan
LLLisheng Liu
Lisheng Liu
LZLilei ZHOU
Lilei ZHOU
SCShi Chen
Shi Chen
JCJiameng Cao
Jiameng Cao
Zhifeng LiuZhifeng Liu
Zhifeng Liu
Water security, the fundamental guarantee for socioeconomic development, is the basic prerequisite for ensuring humans have access to sufficient and safe water resources. In this study, a comprehensive water security evaluation system was constructed from four dimensions: water quantity, water quality, water pollution, and flood disasters. A system-dynamics simulation model for water security was developed. By coupling the Shared Socioeconomic Pathways and Representative Concentration Pathways, predictions were made about the future development trends of China’s water security. The results indicate that China’s water security situation shows significant volatility. The total water supply peaked in 2025. The compliance rate of drinking-water sources reached 98% and stabilized in 2034. The chemical oxygen demand (COD) emissions of industrial and domestic sewage peaked in 2020 and 2034 respectively, and the direct economic losses caused by flood disasters increased cyclically. In future scenario simulations, the water security situation will reach its optimal state under the SSP1-RCP2.6 scenario, while it will be most severe under the SSP5-RCP8.5 scenario. By 2052, the proportion of provinces with an “excellent” level in the water-quantity and water-quality subsystems will reach 52% and 77.4% respectively, mostly concentrated in economically developed regions. The balance between water supply and demand is the primary factor driving changes in water security. These results highlight the necessity of researching the stress factors and stress mechanisms influencing water security in the context of climate change.