01
Urban Digital Twin Platform
Scalable, efficient infrastructure for visualisation, analytics and simulation — the substrate every other workstream builds on.
Live Heatscape NYC — urban heat intervention planner
AI for Cities From urban data to real-world impact
A research group at Cornell Duffield Engineering building intelligent, scalable and interactive models of cities — turning crowdsourced maps, street-level imagery, satellite data and human mobility into tools that researchers, planners and communities can actually use.
Scroll
Cornell Duffield EngineeringSystems Engineering ProgramCenter for Transportation, Environment & Community HealthGlobal Analytics ObservatoryCollege of Architecture, Art, and PlanningUrban digital twinsSpatial AI & reasoningAgentic geospatial intelligencePolicy & deployment
The project
Cities are systems.
We build the tools that let
you reason about them.
AI for Cities develops urban AI and computational tools for understanding complex city systems. We create intelligent, scalable and interactive models of cities that integrate heterogeneous urban data — crowdsourced data from OpenStreetMap, street view and satellite imagery, and human mobility flows.
We use that data and AI to help researchers, planners, policymakers and other stakeholders explore urban conditions, identify patterns, and evaluate potential interventions. The broader goal is an urban intelligence ecosystem that makes advanced city modelling more accessible, and supports better decisions in transportation, housing, climate resilience and infrastructure.
The group sits in the Systems Engineering Program at Cornell Duffield Engineering, and works across computer science, planning, design, policy, environmental science and the social sciences.
Where is the most heat-vulnerable area in New York City? How do building density and street layout affect the prevalence of non-communicable health conditions, such as social isolation, depression, and obesity?
- Home
- Systems Engineering, Cornell Duffield Engineering
- Faculty PI
- Prof. H. Oliver Gao
- Project lead
- Dr. Winston Yap
- Contact
- winyap@cornell.edu
Research themes
Four threads, one stack
Each theme is a layer of the same system: a place to represent the city, a way to reason over it, agents that operate it, and a route into the decisions that follow.
02
Spatial AI and Reasoning
Machine learning and data analytics for high-resolution spatial understanding: flow prediction, anomaly detection, and inference of the patterns cities leave in their data.
03
Agentic Geospatial Intelligence
Agentic tools, servers and knowledge infrastructure that let frontier models reason about places rather than just describe them.
04
Policy & Deployment
Translating research into practice through municipal partnerships, pilot digital-twin deployments, and honest assessment of what changed in the planning decisions that followed.
Projects
Experiential learning
We work closely with student teams and community partners to build real-world solutions to the most pressing urban challenges
Live
New York City
Urban heat
Heatscape NYC
High-resolution crowdsourced insight into extreme heat vulnerability across New York City. 250-metre grid cells score heat risk and system dynamics across 43 indicators.
Live
Causal loop diagrams
System dynamics
URIS Mapper
A human-AI online platform leveraging knowledge graph retrieval for interdisciplinary urban intelligence and systems mapping.
People
The group
One research team spanning systems engineering, computer science, city planning and real estate. Each profile links through to the work behind it.
PI
Lead
Faculty
Faculty
Urban AI Automation Team
Digital Intelligence Team
H. Oliver Gao
PI
Howard Simpson 1942 Professor of Engineering
View profile
Winston Yap
Project Lead
Ezra Systems Postdoctoral Fellow, Systems Engineering
View profile
Charlle Sy
Faculty
Professor of Practice, Systems Engineering
View profile
Suzanne Lanyi Charles
Faculty
Associate Professor of City and Regional Planning and Real Estate
View profile
Krishiv Vora
Urban AI Automation Team
M.Eng. Computer Science
View profile
Andrew Wu
Digital Intelligence Team
B.S. Electrical and Computer Engineering
View profile
Join us
Everyone interested in cities is welcome
The project is deliberately broad: AI modelling, geospatial analysis, 3D visualisation, LLM development, scalable systems architecture, human-centred design, community and stakeholder engagement, policy and evaluation, ethnographic research, and the conceptual work of describing how urban technologies are actually understood and used.
Students with design and social-science backgrounds are particularly encouraged, and can contribute through UI/UX research and design, user surveys, usability testing, participatory workshops, interviews and focus groups.