YWYuan Wang

Yuan Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Yuan Wang has a total of 42 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From physical surfaces to human-centric heat stress: LST and UTCI heat mapping reveals nonlinear effects of urban morphology

    by Yuan Wang, Shengao Yi, Xiaojiang Li, Pengyuan Liu, Zhiwei Yang, Ronita Bardhan, Rudi Stouffs


  • Zoning effect on urban heat exposure risk: comparing four typical spatial zoning approaches

    by Junmao Zhang, Meixia Lin, Jiayi Fu, Yuan Wang, Tao Lin, Yuan Chen, Hongkai Geng, Zixu Jia, Yicheng Zheng, Xia Yao


  • Living upon networks: A heterogeneous graph neural embedding integrating waterway and street systems for urban form understanding

    by Pengyuan Liu, Yuan Wang, Stef De Sabbata, Binyu Lei, Filip Biljecki, Jing Tang, Rudi Stouffs

    Cities are supported by multiple, interacting networks, most prominently streets, which channel movement and economic exchange, and, in many contexts, waterways, which regulate flows of goods, people, and environmental amenities. Conventional quantitative studies of urban form have tended to privilege streets alone, limiting their ability to capture the full spatial logic of the urban fabric. This paper introduces a Heterogeneous Graph Autoen-coder (HeterGAE) that jointly embeds street and waterway systems, providing a unified, graph-based representation of urban form. Using Singapore as a case study, we train HeterGAE embeddings and employ them in two downstream tasks: predicting daytime and night-time land-surface temperature (LST) and estimating resale prices of public housing. Relative to a baseline model that encodes streets only, the dual-network embeddings improve predictive accuracy by about 20% for both tasks, confirming that natural and built infrastructures make complementary contributions to urban socio-environmental processes. By capturing the interaction between street junctions and waterway nodes within a single latent space, the proposed approach provides a flexible template for GeoAI-assisted urban analytics in diverse settings. The results underscore the value of integrating heterogeneous urban networks in evidence-based planning and highlight the potential of graph-neural techniques for developing more nuanced and sustainable urban strategies.


  • Open Access

    Revealing the impact of 2D/3D urban morphology on spatial heterogeneity of diurnal and nocturnal UHI through X-GeoAI driven analytics

    by Yuan Wang, Pengyuan Liu, Rudi Stouffs

    Urban morphology plays a pivotal role in shaping urban heat islands (UHI), especially in high-density cities, by influencing land surface temperature (LST) and air temperature. While previous studies have explored the relationships between urban morphology and temperature, they often fail to simultaneously capture the nonlinear interactions of these relationships and spatial heterogeneity arising from regional variations in urban form and environmental conditions. Furthermore, the varying influence of urban morphology on diurnal and nocturnal UHI remains insufficiently understood. This study bridges this gap by applying Geographically Weighted Machine Learning (GWML) and Graph Neural Network (GNN) models to investigate the non-stationary relationships between UHI and its influencing factors. Using high-resolution diurnal and nocturnal LST data from Landsat and ECOSTRESS, combined with 3D building morphology metrics (e.g., Sky View Factor), road network attributes, socio-demographic characteristics, and landscape indices, we systematically analyse the spatial variations in these associations. The analysis includes calculating Moran’s I to detect spatial patterns and comparing the predictive performance of GWML and GNN against Geographically Weighted Regression (GWR). SHapley Additive exPlanations (SHAP) enhance interpretability of explainable GeoAI (X-GeoAI) models, revealing localized impacts of key influencing factors. Our findings demonstrate significant spatial variations in the effects of 2/3D urban morphology on UHI across diurnal and nocturnal cycles. These insights provide a robust foundation for targeted UHI mitigation strategies and adaptive urban planning. This work highlights the potential of advanced GeoAI methods in urban climate research and offers actionable pathways for enhancing climate resilience in high-density cities.


  • Open Access

    Unveiling Dynamic Heat Exposure Patterns: The Intersection of Human Mobility and Environmental Heat Metrics Using Mobile Phone Data in Urban Areas

    by Yuan Wang, Jiazu Zhou, Rudi Stouffs

    Cities are increasingly vulnerable to extreme heat events due to climate change, particularly in densely populated urban areas where heat exposure is intensified by the urban heat island effect. Traditional assessments of heat exposure often rely on static metrics, such as fixed thermal environmental data or residential population maps, which fail to account for the dynamic nature of human mobility. It remains unclear whether human mobility exacerbates or alleviates urban heat exposures of populations in cities, especially in high-density urban areas. This study integrates anonymized mobile phone location data with environmental heat indices to analyse spatiotemporal heat exposure patterns in Singapore. By analysing human mobility patterns with mobile phone data at a fine-grained spatial resolution, we identify hotspots of human activity and heat exposure during specific times of the day, such as work hours and evening commutes. The results highlight significant differences between static and dynamic heat exposure assessments, emphasizing the critical role of mobility in shaping the spatial-temporal patterns of heat exposure. This work provides practical guidance for urban climate adaptation, including the strategic placement of heat shelters, prioritization of urban greening in activity hotspots, and improved zoning policies. Our findings also contribute to enhancing urban resilience and public health outcomes in response to the challenges of climate change.

  • Open Access

    Patterns of nighttime urban heat island patch in mega urban agglomerations: a case study in the Pearl River Delta, China

    by Han Wang, Tengyun Yi, Yanchi Lu, Yuan Wang, Jiansheng Wu

    Urban heat islands (UHI) effects across metropolitan areas poses substantial threats to both ecosytems and local residents with the risks associated with intensifying nighttime temperature, however, the patterns and evolution of nighttime UHI remain poorly understood. Taking the Pearl River Delta (PRD) in China as a case of mega urabn agglomeration, this study first integrated geostatistical models and exponential decay models to extract the urban heat island patches (UHIP) from 2003 to 2019, then evaluated the UHI effects and spatial patterns of UHIP, and finally investigated the influencing factors of the nighttime UHI intensity (UHII). The results showed that: (1) a significant clustering pattern of nighttime UHII and an increasing trend of annual nighttime UHII were observed. (2) Patch expansion categories revealed diverse UHI evolution modes, of which the spatial-temporal dynamics were found with landscape metrics, and the UHII in enclave-type, infill-type, and edge-type patches decreased successively. (3) Socioeconomic factors showed a significant positive correlation with UHII, simultaneously, environmental and landscape factors exhibited spatially dependent impacts both within and outside the UHIP. These findings underscore the need for urban planning strategies considering the heterogeneity and dynamics of nighttime UHI towards climate adaptation and urban resilience improvement in mega agglomerations.

  • Open Access

    Impacts of Air Pollutant Emissions on Solar Energy Generation

    by Fei Yao, Paul Palmer, Jianzheng Liu, Hongwen Chen, Yuan Wang

    Particulate matter (PM) in the atmosphere and deposited on solar photovoltaic (PV) panels reduce PV energy generation. Reducing anthropogenic PM sources will therefore increase carbon-free energy generation. However, we lack a global understanding of the sectors that would be the most effective at achieving the necessary reductions in PM sources. We combine well-evaluated models of solar PV performance and atmospheric composition to show that deep cuts in air pollutant emissions from the residential sector substantially benefit Asian PV power output. Specifically, halving residential emissions of PM would lead to an additional 10.3 TWh yr-1 and 2.5 TWh yr-1 of PV energy generation in China and India in 2020, respectively. Compared to the 2020 electricity generation of 261.6 TWh yr-1 and 54.4 TWh yr-1 from solar PV technology in China and India, respectively, these unrealised sources of energy generation represent an improvement of approximately 4-5%. While anthropogenic PM sources originate mainly from producers, they are responding to changes in domestic and international consumer demand. This raises a critical question about the extent to which consumers, who benefit from the emission process, should be responsible for the resulting unrealised, cleaner PV energy generation. Focusing on Northeast Asia (NEA), we investigate the source-receptor relationship of PV energy losses attributable to PM pollution among China, South Korea, and Japan by incorporating a new input-output model into the combined models of solar PV performance and atmospheric composition. Our findings reveal that the solar energy generation losses attributable to PM pollution in NEA caused by emissions produced in China surpass those linked to China’s consumption that stimulates emissions in China and elsewhere, with the disparity amounting to 9.3 TWh yr-1. Conversely, a reverse pattern is observed for solar energy generation losses linked to emissions produced versus induced by consumption in South Korea and Japan, where the disparities are found to be -0.023 TWh yr-1 and -0.231 TWh yr-1, respectively. In other words, when we consider international trade across NEA, we find there is diminished (augmented) responsibility for China (South Korea and Japan) in explaining PV-related energy losses attributable to PM pollution.