Artificial Intelligence Unlocks the Secrets of Neighborhood Change

Researchers at MIT and Harvard believe that their computer vision system (i.e., artificial intelligence) helps reveal fundamental characteristics of neighborhood change.

1 minute read

July 14, 2017, 8:00 AM PDT

By James Brasuell @CasualBrasuell


Larry Hardesty shares news of a new "computer vision system" from MIT's Media Lab, created with partners from Harvard University, that quantifies "the physical improvement or deterioration of neighborhoods in five American cities."

In work reported today in the Proceedings of the National Academy of Sciences, the system compared 1.6 million pairs of photos taken seven years apart. The researchers used the results of those comparisons to test several hypotheses popular in the social sciences about the causes of urban revitalization. They find that density of highly educated residents, proximity to central business districts and other physically attractive neighborhoods, and the initial safety score assigned by the system all correlate strongly with improvements in physical condition.

The new tool is built on a system created four years ago, which analyzes "street-level photos taken in urban neighborhoods in order to gauge how safe the neighborhoods would appear to human observers."

Hardesty goes into a lot more detail about the ideas that contributed to the creation of the computer vision system, and the findings that have been produced in its deployment.

Linda Poon offers additional insight into the use of artificial intelligence in the analysis of urban conditions

Thursday, July 6, 2017 in MIT News

Aerial view of homes on green hillsides in Daly City, California.

Depopulation Patterns Get Weird

A recent ranking of “declining” cities heavily features some of the most expensive cities in the country — including New York City and a half-dozen in the San Francisco Bay Area.

April 10, 2024 - California Planning & Development Report

Aerial view of Oakland, California with bay in background

California Exodus: Population Drops Below 39 Million

Never mind the 40 million that demographers predicted the Golden State would reach by 2018. The state's population dipped below 39 million to 38.965 million last July, according to Census data released in March, the lowest since 2015.

April 11, 2024 - Los Angeles Times

Large blank mall building with only two cars in large parking lot.

Pennsylvania Mall Conversion Bill Passes House

If passed, the bill would promote the adaptive reuse of defunct commercial buildings.

April 18, 2024 - Central Penn Business Journal

Young woman and man seated on subway car looking at phones.

Google Maps Introduces New Transit, EV Features

It will now be easier to find electric car charging stations and transit options.

7 hours ago - BGR

Ohio state capitol dome against dramatic lightly cloudy sky.

Ohio Lawmakers Propose Incentivizing Housing Production

A proposed bill would take a carrot approach to stimulating housing production through a grant program that would reward cities that implement pro-housing policies.

April 19 - Daytona Daily News

Aerial view of Interstate 290 or Eisenhower Expressway in Chicago, Illinois.

Chicago Awarded $2M Reconnecting Communities Grant

Community advocates say the city’s plan may not do enough to reverse the negative impacts of a major expressway.

April 19 - Streetsblog Chicago

News from HUD User

HUD's Office of Policy Development and Research

Call for Speakers

Mpact Transit + Community

New Updates on PD&R Edge

HUD's Office of Policy Development and Research

Urban Design for Planners 1: Software Tools

This six-course series explores essential urban design concepts using open source software and equips planners with the tools they need to participate fully in the urban design process.

Planning for Universal Design

Learn the tools for implementing Universal Design in planning regulations.