Urban Sensing and Analytics

Leveraging a variety of sensing data, such as street view and satellite images, the HUB Lab excels in employing advanced techniques, including computer vision and GeoAI, for precise evaluation of the urban environment (e.g., built characteristics, urban greenery, street trees, and pedestrians). Our unwavering dedication to advancing the understanding of the built environment establishes a foundational framework for cutting-edge research at the intersection of environment, behavior, and health. Our contributions aim to foster a profound connection between the planed environment and the well-being of individuals and communities.

Related works

Liu, D., Wei, D., Ho, H. C., Li, M., & Lu, Y. (2026). Linking window-view nature exposure with health and wellbeing outcomes: Using photorealistic 3D city models and computer vision technique. Landscape and Urban Planning, 270, 105601. (see more details)

Liu, F., Lu, Y., Song, Q., Qiu, W., & Liu, D. (2025). The association of subjective physical disorder and pedestrian volume: A big urban data and machine-learning approach. Computers, Environment and Urban Systems, 122, 102348. (see more details)

Liu, D., Lu, Y., & Jiang, Y. (2025). Exploring the environmental justice of street tree provision: Adding biodiversity to automatic assessment of street-level greenery. Urban Forestry & Urban Greening, 129184. (see more details)

Nexus between Environment, Behavior, and Health

The HUB Lab specializes in conducting both cross-sectional studies to investigate correlation relationships among environment, behavior, and health, and longitudinal studies to infer causal relationships. This dual expertise allows us to comprehensively demonstrate the complex interplay between environmental factors, individual behaviors, and health outcomes. Our ultimate goal is to establish a systematic and holistic framework that provides valuable insights for achieving healthy cities, offering a comprehensive illustration of the underlying nexus between environment, human behavior, and health.

Related works

Li, Z., Lu, Y., Wang, J., & Wu, Y. (2026). Rail transit and travel satisfaction: Evidence from a natural experiment in Wuhan. Travel Behaviour and Society, 43, 101211. (see more details)

Zhou, Y., & Lu, Y. (2025). Experienced economic segregation and associated mental health inequalities across urbanicity. Social Science & Medicine, 118813. (see more details)

Zou, X., Lu, Y., & Zhou, Y. (2025). Threshold effects between spatial access to medical resources and life expectancy: a 19-year longitudinal study in Hong Kong. Social Science & Medicine, 118654. (see more details)

Zhou, Y., & Lu, Y*. (2024). Health effects of greenspace morphology: Large, irregular-shaped, well-connected, and close-clustered greenspaces may reduce mortality risks, especially for neighborhoods with higher aging levels. Environmental Research, 263, 120095. (see more details)

Geospatial Big Data Mining and Spatial Modelling

Drawing on multi-source geospatial big data (e.g., social media data, VGIs, GPS-based data, and remote sensing data), the HUB Lab seeks to employ a diverse set of GIS techniques, such as spatiotemporal visualization, modelling, and simulation to uncover compelling patterns and phenomenon within cities across space and time. Our research contributes to the elucidation of complex urban dynamics, providing valuable insights for evidence-based decision-making in urban planning and advancing the pursuit of sustainable urban development.

Related works

Wu, X., Lu, Y., Wei, D., & Chen, W. Y. (2025). The racial inequity of park visitation behavior in the post-pandemic era. Travel Behaviour and Society, 41, 101105. (see more details).

Jiang, Y., Sun, Z., Wei, D., Zhao, P., Yang, L., & Lu, Y. (2025). Revealing the spatiotemporal pattern of urban vibrancy at the urban agglomeration scale: Evidence from the Pearl River Delta, China. Applied Geography, 181, 103694. (see more details)

Chen, L., & Lu, Y. (2025). Exploring dual-directional collective human mobility vulnerability and the built environment in places: Lessons from the COVID-19 pandemic. Travel Behaviour and Society, 40, 101031. (see more details)

Chen, L., & Lu, Y. (2025). Investigating dual-directional collective human mobility patterns of place-level incoming and outgoing travel behaviors using big data. Journal of Transport Geography, 125, 104215. (see more details)

Research Grants

6. PI: Urban Greenness and Urban Residents’ Health: A Novel Method to Assess Street Greenery. University Grants Committee of Hong Kong, General Research Fund, 01/01/21 - 31/12/24.

5. PI: Urban Built Environment Optimization Strategies Based on Analysis of Outdoor Activities for School-Aged Children. (基于学龄儿童户外活动分析的城市建成环境优化策略). National Science Foundation of China, General Program, 01/01/18 - 31/12/21.

4. Co-PI: Grand Theaters in China from 1998 to 2015: A Study of their History, Public Space, and Design Language. University Grants Committee of Hong Kong, General Research Fund, 01/01/17 - 21/04/21.

3. PI: Identifying Physical Activity and Built Environment Factors Associated with Children's School Transportation Modes in Hong Kong. University Grants Committee of Hong Kong, General Research Fund, 01/01/17 - 22/06/20.

2. PI: Effect of the Physical Environment on the Walking Behavior of Elderly People Living in High-density Large-scale Building Complex: A Case of Hong Kong Public Housing. University Grants Committee of Hong Kong, General Research Fund, 01/01/16 - 11/06/19.

1. PI: A Comprehensive Measurement System and Design Strategies for the Walkability of Urban Community Built Environments. (城市社区建筑环境步行效能的综合度量体系和设计策略). National Science Foundation of China, General Program, 01/01/16 - 31/12/19.