Elizabeth Roberto
Rice University, TX·Social Science·Early-career
Roads, walls and other physical features of a city can quietly shape who lives where and how easily people reach schools, parks and services. Yet the role of this built environment in creating social and spatial differences between neighborhoods has received little study.
- Fields
Social Science
Computer Science
- Topics
built environment
urban infrastructure
road network connectivity
- Grants
- 1 known grant, through Jun 2030
What they work on
- Measure how road network connectivity relates to residential spatial variation and proximity to local public services across U.S. cities, using spatial and network analysis of road networks and demographic data.
- Identify which built-environment features, such as disconnected roads and physical barriers, create social and spatial divisions, using AI image classification of satellite and street-view images.
- Trace the origins and evolution of these built features using historical maps and records.
- Test how these features have shaped home valuation, and how valuation practices persist in property appraisals, using housing market data and machine learning analysis of texts.
More about the research
This project asks how historical and present-day views of urban space become built into infrastructure, such as disconnected roads and physical barriers, across U.S. cities. It also asks how this infrastructure contributes to differences between places.
Why it matters
Understanding how disconnected roads and physical barriers divide neighborhoods could help city planners, policymakers and community groups see where infrastructure limits access to public services. It could also show how these features have shaped home values and property appraisals. A public web tool will share the findings and methods with residents and decision-makers working on housing and urban policy.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Constantine Kontokosta
New York University, NY·Social Science
Identify representativeness bias in smartphone mobility data, meaning which groups are over- or undercounted, and develop methods to correct it.
Howard Liu
University of South Carolina-Columbia, SC·Social Science
Develop the GeoRDyn toolkit, combining AI, computer science and statistics to model the spatial and relational complexities of collective-action events in fine-grained data.
Wenfei Xu
Cornell University, NY·Social Science
Build a public, geocoded dataset of roughly 280,000 FHA-insured and VA-guaranteed mortgages from land records in 20 U.S. counties spanning 40 years.
The school
Rice University: 24 labs on PI Pages, $278M a year on research, 267 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.