Hello! I am Mingze Chen, Ph.D. Candidate at the Urban Nature Design Research (UNDER) Lab, University of British Columbia (UBC). I’m joining Senseable City Lab, Massachusetts Institute of Technology (MIT) as an echange student. My research focuses on the interdisciplinary application of big data and machine learning technologies in landscape and urban planning.
I hold a Master of Architecture in machine learning urbanism and worked as a research associate at The Bartlett Faculty of the Built Environment, University College London (UCL).
I have published over 25 peer-reviewed journal articles in leading international journals such as the Habitat International, Journal of Environmental Management, Urban Forestry & Urban Greening, and Energy and Buildings, etc. I presented my work at major academic conferences, including ACSP, CELA, IFLA, and EDRA. I am also actively involved in teaching, serving as a sessional lecturer and adjunct fellow at institutions in Canada, the United States, and China.
I am the founder of Nature AI Lab, a research platform that integrates cutting-edge technologies with urban and nature studies to create data-driven solutions for a more resilient, equitable, and livable future—embodying our vision: Better Technologies, Better Nature, Better Life.
Contact: mingze.chen@ubc.ca
For more about my research and design, please visit my Google Scholar Profile, Design Portfolio, and LinkedIn.
Download my CV (updated Nov 2025)
My research interest focuses on Human-Nature-Urban Intelligence, including:
Theme I. Vision-language Model for Urban and Nature Analytics
Developing multimodal AI frameworks (Computer vision and/or Large Language Models) to quantify vitality, inclusiveness, and behavioral patterns in urban and natural spaces.
Theme II. Sensor-based and Geospatial Modeling of Human-nature Relationship
Leveraging multi-source geospatial data (POIs, street view imagery, social media, and smartphone-GPS traces) with tools (GIS, remote sensing, and UAVs) to evaluate the spatial diversity, accessibility, and social equity of human–nature interactions.
Theme III. Climate Resilience and Wellbeing in Urban Landscapes
Exploring the intersection of environmental comfort, public health, and urban resilience by combining microclimate monitoring, machine learning, and geo-design approaches.
Theme IV. Computational Design and Visualization Technologies
Integrating Rhino–Grasshopper, AI diffusion models, web-based visualization (HTML/CSS/JS), and GIS workflows to support parametric design and mapping.
Collaborators
