Environmental justice that can be measured, mapped, and acted on.
I study how urban green space, thermal exposure, and street-level conditions vary across communities, using remote sensing, LiDAR, and imagery to surface uneven urban experience.
Urban AI • Equity • Mobility
Designing data-driven tools for fairer urban futures.
I am Xuanyu Zhou, recently graduated from Zhejiang University with a degree in Urban and Rural Planning, and a former exchange student at UC Berkeley CED. I will join the University of Pennsylvania Master of City Planning program in Fall 2026. My work brings together urban equity, mobility, resilience, remote sensing, and machine learning, with a growing interest in how LLMs and Urban AI can support planning practice.
- Home base Recent graduate from Zhejiang University, Penn MCP from Fall 2026, with research experience spanning Hangzhou, Berkeley, Pittsburgh, Seattle, and the Bay Area.
- Methods Remote sensing, LiDAR, street view imagery, geospatial machine learning, simulation, and computational urban analytics.
- Current arc Building bridges between rigorous planning research and emerging Urban AI tools that can support real decisions.
- Looking ahead Heading to Penn MCP in Fall 2026, open to research and practice collaborations now, and looking toward future job opportunities.
Planning researcher with one foot in spatial data and the other in design, always looking for clearer ways to ask urban questions.
Now Exploring
How LLMs, simulation, and spatial intelligence can help planners reason across mobility, exposure, and urban inequality without losing the human scale.
2024–26
Recent work across ACSP, EDRA, TRB, and collaborative lab research.
3
Core themes: environmental justice, urban mobility, and resilience.
Hybrid
A practice that mixes planning theory, spatial data, and experimental AI workflows.
Research Interests
Three lenses shape the questions I keep returning to.
I am most interested in urban analytics that stay technically rigorous while remaining legible to planning, policy, and everyday city life.
Transportation futures shaped by simulation instead of hype.
From Urban Air Mobility to shared mobility, I build computational frameworks that test how next-generation transport systems might work in real metropolitan conditions.
Urban form as a living infrastructure for recovery and wellbeing.
I use geospatial machine learning to connect built environment characteristics with post-pandemic recovery, community vitality, and public health outcomes.
Selected Work
A compact map of the problems I have been building through.
These projects sit at the intersection of planning, computation, and public impact, and together they sketch the shape of my current research agenda.
Urban Mobility
Urban Air Mobility
Optimizing UAM demand, fleet operations, and ground access through a large-scale simulation framework for the San Francisco Bay Area.
Open project
Equity & Green Space
Urban Green Space
Examining how green space distribution, morphology, and use shape vitality and equity in shrinking cities, with Pittsburgh as a case study.
Open project
Resilience & Health
Urban Built Environment
Investigating how built form influences post-pandemic recovery, shared mobility co-benefits, and emotional geographies in rapidly changing cities.
Open project
News & Updates
Recent steps that moved the work forward.
A few milestones from the last two years, from preprints and presentations to collaborative research.
Graduated from Zhejiang University.
Completed the Urban and Rural Planning degree and received university-level Outstanding Graduate and college Outstanding Undergraduate Thesis honors.
Submitted PedSVF to ACM SIGSPATIAL 2026.
The pedestrian-scale sky view factor study is under review at the 34th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.
Accepted by Geoinformatics 2026.
The pedestrian-centered multi-view-factor mapping work will be presented at the National University of Singapore in July 2026.
Released the UAM study as an arXiv preprint.
Shared the demand analysis and fleet optimization framework publicly, extending the MIT-UF-NEU summer research collaboration.
Presented at the Transportation Research Board 2026 Annual Meeting.
Presented the UAM study in Washington, D.C., extending the summer camp work into a broader transportation audience.
Along The Way
A research path built through labs, studios, and cross-disciplinary mentors.
My trajectory has been less about a single topic than about learning how to connect methods, places, and collaborators into a coherent research practice.
Qizhenwenxue Undergraduate Research Program
I began by studying post-pandemic urban resilience with Geographically Weighted Random Forest, linking recovery rates to the built environment in Nagoya.
Urban Green Space in shrinking cities
Working with Mingze Chen, I led a time-lagged study of Pittsburgh that connected machine learning, green space equity, and shrinking city revitalization.
Pedestrian-scale Sky View Factor mapping
At the 3M Lab, I contributed to PedSVF, a multimodal aerial-street grounding study for pedestrian-scale SVF estimation, now under review at ACM SIGSPATIAL 2026 and accepted by Geoinformatics 2026.
From spatial analytics to large-scale mobility systems
The summer research camp sharpened my interest in computational transportation research and shaped how I hope to carry large-scale mobility work into Penn MCP.
Open Door
Always happy to talk about cities, methods, and what comes next.
If you are building a research project, lab collaboration, practice initiative, or future job opportunity that lives somewhere between planning and computation, I would love to hear about it.
What I bring
A planning perspective grounded in spatial data, careful quantitative methods, and a genuine interest in making technical work legible to broader audiences.