New Paper: Evaluating the spatial-temporal impact of urban nature on urban vitality in Vancouver: A social media and GPS data approach
Land Use Policy has published our new paper on developing a novel machine learning framework to assess how urban greenery influences urban vitality across spatial and temporal scales. By integrating seasonal remote sensing data with social media based vitality indicators. The study reveals that natural elements such as vegetation coverage (NDVI), blue-green connectivity (BGCI), and land surface temperature (LST) affect daytime and nighttime vitality in different ways. Especially across working days and holidays.
Nature AI Lab
2025-10-28
New Paper: Who gets to use the street? Evaluate the utilization and inclusiveness using crowdsourced videos and vision-language models
Our new study is published in Sustainable Cities and Society. This study introduces a scalable framework combining crowdsourced street videos from delivery riders (EgoCity dataset) and a custom vision-language model (LLaVA-PI) to evaluate public street space (PSS) through two indicators: utilization and inclusiveness. Results show a structural mismatch, while adults dominate high-activity streets, children and elderly residents are underrepresented, even in neighborhoods where they live in large numbers. Only 4.9% of streets achieve both high utilization and high inclusiveness. This framework offers a new AI-powered lens for diagnosing spatial inequality and supporting just urban design.
Nature AI Lab
2025-10-27
Conference：The 2025 ACSP Annual Conference in Minneapolis
Thrilled to participate in the 65th Annual Conference of the Association of Collegiate Schools of Planning (ACSP2025), held from October 23 to 25, 2025, in Minneapolis, Minnesota. As one of the premier global platforms for academic exchange and professional dialogue in urban planning, the conference brought together scholars, practitioners, and students to explore planning theory, applied innovation, and cross-sector collaboration. Led by Mingze Chen, team members Xiamengwei Zhang, Yidong Yang, and Xiao Wang joined academic sessions, case study discussions, and professional networking events. They engaged in meaningful exchanges on research application and interdisciplinary methods, gaining valuable perspectives to support future research and project development.
Nature AI Lab
2025-10-26
Guest Lecture: Generative Model for Urban Design and Planning
We were honored to welcome Guanhong Li from the National University of Singapore to Nature AI Lab for an inspiring guest lecture. His research on diffusion models and LLMs in urban design, cultural modeling, and planning evaluation reminded us of the human and practical possibilities behind generative AI.
Nature AI Lab
2025-10-19
New Paper: Comparative Analysis of Greenery Inequalities in New York and London: Social-economic and Spatial Dimensions
Urban Forestry & Urban Greening has published our new comparative study on the socio-spatial drivers of urban green space (UGS) inequality in New York City and London. We integrate multiscale spatial modeling (OLS, GWR, MGWR) with high-resolution census and land use data to uncover how income level, race, education, and built environment shape green accessibility across neighborhoods. The study uncovers striking spatial heterogeneity between the two cities. It further identifies sharp contrasts shaped by policy decisions. Together, these patterns demonstrate how planning histories and institutional frameworks influence environmental justice outcomes.
Nature AI Lab
2025-07-27
New Paper: Urban Scene Types and Heat Island Risk in NYC – Insights from Interpretable Machine Learning
Urban Climate has published our new study on urban scene characteristics and the urban heat island effect in New York City. We apply interpretable machine learning (SHAP, ALE, and counterfactual analysis) to reveal how building height, vegetation coverage, and socio-economic disparities shape land surface temperature. These findings provide actionable insights for climate-resilient and equitable urban planning.
Nature AI Lab
2025-07-27
New Paper: Urban Amenity Equity for People with Disabilities in London – Insights from Multiscale GWR.
Habitat International has published our new study on urban amenity equity for people with disabilities in London, which employs multiscale GWR to uncover pronounced disparities—especially in access to high‑quality green spaces and commercial areas—and calls for data‑driven, disability‑inclusive urban planning.
Nature AI Lab
2025-05-05
Collaboration Insight: At the Intersection of AI and Urban Landscapes – Visit to Meta Boston.
Special thanks to Marcie Hogan for the warm welcome and thoughtful tour! Grateful for the opportunity to visit the Meta Boston office and inspired by the fusion of art and technology throughout the space.
Nature AI Lab
2025-05-03
New Paper: Perception vs. Physical Environment in Shaping Public Visitation Thresholds Across COVID-19 Stages.
Urban Forestry & Urban Greening has published our new study on COVID-era public space visitation in Las Vegas, which integrates machine learning, GPS, and review data to compare the nonlinear impacts of environmental features and human perception—highlighting the divergent resilience of parks and commercial areas, and calling for perception-informed, adaptive urban design.
Nature AI Lab
2025-04-30
New Paper: Measuring Pedestrian-Level Street Greenery Visibility with Space Syntax and Crowdsourced Imagery
Our latest study in London, UK, examines an innovative framework to quantify and map how pedestrians perceive urban greenery, utilizing advanced space syntax metrics and crowdsourced imagery for more informed urban planning and design.
Nature AI Lab
2025-02-15
New Paper: Measurement Tools and Senior Engagement in Urban Nature
Health & Place publishes our systematic review on tools for measuring senior behaviors in urban nature, highlighting health benefits and behavioral patterns.
Nature AI Lab
20245-01-06
New Paper: Advancements in supervised machine learning for outdoor thermal comfort
Energy & Buildings publishes our systematic review on advancements in supervised machine learning for outdoor thermal comfort, highlighting scales, applications, and data types to refine predictive methodologies and address urban climatic challenges.
Nature AI Lab
2024-01-02
New Paper: The “Blue” Habitat of Urban & Suburban Areas and approaches for its biodiversity research
Journal of Environmental Management publishes our scoping review on the ‘Blue’ Habitat of Urban and Suburban Areas, analyzing aquatic ecosystems, biodiversity challenges, and innovative methodologies to foster interdisciplinary collaboration for sustainable conservation in urban planning.
Nature AI Lab
2024-12-15
Conference：The 2024 ACSP Annual Conference in Seattle
Thrilled to present our team’s recent research at the #2024ACSP Annual Conference in Seattle: “Defining Urban Vitality Using Image-based, Text-based, and GPS Data” under the guidance of my supervisor Dr. Keunhyun Park.
Nature AI Lab
2024-11-20
