AivexaNewsSearch
AI news for builders and product teamsChecked every hour

The promise and peril of using visual AI to study cities

Collected Sep 30, 2026

MIT researchers have published a new book examining the use of visual artificial intelligence in urban studies, along with its risks. "How AI Sees the City: Urban Visual Intelligence" was published this month by Routledge. Its authors are Fábio Duarte, a principal research scientist and associate director of the MIT Senseable City Lab; Martina Mazzarello, a research scientist and lead of the lab's global initiatives; Carlo Ratti, a professor of the practice and founder and director of the lab; and Fan Zhang, an assistant professor at the Institute of Remote Sensing and GIS at Peking University.

The book stems from work at the MIT Senseable City Lab, founded in 2004. A few months ago, researchers from the lab published a study on pollution in New York City that used machine learning to identify vehicle types appearing in 331 traffic cameras in the city and estimate emissions from each automobile. The authors say visual AI can address questions about traffic congestion, intersection safety, and which parts of plazas or parks attract the most people. They also discuss urban greenery and cite a recent Senseable City study using images from 400,000 AirBnB listings worldwide, which showed interior design styles are not becoming globally more homogeneous but reflect significant geographic differences.

The authors place AI within a longer tradition of visual urban studies, citing Kevin Lynch, a former MIT professor whose 1960 book "The Image of the City" influenced many scholars, and sociologist William H. Whyte, who examined public spaces. "Kevin Lynch at MIT was only using paper and pen," Duarte said. "We can now scale up what he was doing, with visual AI, while also looking at many different dimension of cities."

The book also outlines potential problems, including the intrusiveness of widespread visual surveillance and the potential for bias to be reinforced through AI systems. The authors write that in evaluating potential safety gains from intensive video recording, "the benefits must be weighed against the significant erosion of personal freedom and the potential for abuse inherent in a system of constant monitoring." They note London has about 210 cameras per square mile, while eight of the world's 10 most camera-heavy cities are in China, with Shanghai having over 5,000 per square mile, and that debate over traffic cameras arose in the U.S. this year. On bias, Duarte said AI models trained on majority population groups may not evaluate minority groups the same way, adding, "AI is not neutral." Mazzarello said, "our eyes are not neutral, either."

Michael Batty of University College London called it a "fascinating book" that "shows how we are beginning to interpret the world of urban design, suggesting ways in which we might improve design using urban analytics, AI and large language models." The authors conclude, "We should explore this wisely, critically, and creatively."

Read at MIT News · AI

Based on reporting from the original publisher. Visit the source for full context and later updates.

Publisher excerpt

In their new book, “How AI Sees the City,” the leaders of MIT’s Senseable City Lab examine the technology’s implications for researching urban life.