Machine Learning is helping researchers analyze Google Street view of cities to determine the amount of the urban change happened over the years.
Why are certain neighbourhoods safe while some other feel dangerous? Why are few others considered beautiful? How do cities develop and above all, change over time? And most importantly, can we quantify these observations about the way we perceive cities? And maybe use it to plan urban areas that are more equitable?
César Hidalgo, the director of the Collective Learning group at the MIT Media Lab, has spent years using crowdsourced data and machine vision technology to build models of cities that can answer questions that statistics and surveys have not been able to, so far.
Hidalgo’s work illustrates that as AI has colonised our daily lives–from Barbie dolls to web design, it is safe to say that it has also started to infiltrate our academic study, particularly when it comes to how we understand cities. But as this nascent field develops, it’s faces its own challenges.
What Makes a Neighbourhood Change?
In the group’s latest paper, photos of five cities taken seven years apart of Google Street View are analysed several to know about what causes urban revitalisation. It’s a critical issue that’s been studied for decades, with much debate surrounding several schools of thought about how and why revitalisation occurs. Hidalgo and histeam were able to put some of those “classical” ideas about cities to the test by parsing 1.6 million Street View photos as evidence using machine learning.
The major finding is that income level is an indicator of neighbourhood change. The team also found that the biggest factor in positive urban change was the amount of highly educated people residing in a neighbourhood.
Studies have suggested proximity to aesthetically beautiful neighbourhoods and to business districts are also correlated. But surprisingly, and contrary to some theories, Hidalgo found that income and housing cost aren’t correlated with positive or negative physical change in a neighborhood. This made Hidalgo conclude that the changes in the cities is more of a skill story than it was as earlier considered as the income story. Meaning that if there are rich people in the neighbourhood then it doesn’t mean they happen to be more educated.
Meanwhile, their model supported other theories, like the notion that neighbourhoods that start out with positive appearances experience greater improvement. Their findings can be explored in an interactive called Street Change that includes maps of New York, Boston, Detroit, Washington, D.C. and Baltimore, shaded by the system’s rating of how dramatic the urban change was in a particular neighbourhood.
Studies like this one, which use machine learning to further our understanding of urbanism, could transform the discipline into more of a science than a social science.
From Social Science to Science
However, there are still plenty of challenges with using machine learning in this context. The biggest one of the is of course, Data.
Much of the data from Hidalgo’s previous studies using computer vision was crowd-sourced from a site he and his colleagues built called Place Pulse. There, users could rate how safe and beautiful a street scene seemed to them, giving the researchers data about how people perceive streets. But in order for Hidalgo to take the project global, he’ll need a lot more data–especially given that a program trained on New York and Boston wouldn’t fare so well if pointed at foreign urban centers. So far they’ve relied on the organic growth of Place Pulse users to feed their machine learning data set, but, to truly expand, Hidalgo says they may have to pay for people to rate city scenes on Amazon’s crowd-working site Mechanical Turk–or advertise on Facebook.
But the challenges of this approach to research don’t end once the data has been acquired. Cities are constantly changing–they’re dynamic places, and not every image is ideal for an algorithm to process. Hidalgo says that Nikhil Naik, a postdoc at MIT’s Abdul Latif Jameel Poverty Action Lab and the lead author on the new paper, spent years working on the data set the team ended up using for the paper. Chief among the challenges was parsing Google Street View images that might look drastically different in the before and after–but only because there’s a giant truck in the way in one of them. The team also had to correct for seasonal changes, like snow on the ground or stormy skies.
To fix these aberrations in the data, the researchers had to categorise the real-life object depicted in every pixel of the 1.6 million images in the database. If there were too many pixels that had been identified as belonging to a truck or a pedestrian, the program wouldn’t use that exact image, swapping it out for similar images on the same block. The system was also trained to ignore things like trees and skies, which change too much during different seasons to give an accurate impression of change.
The real challenge lies in taking the research from academia and out onto the streets, so to speak. We have got ways to go for methods that are common in urban planning. However, these methods needs to be scaled better. They also need to be incorporated into tools that put them into hands of planners and architects themselves.
Still, the promise of machine learning is already tangible through work like Hidalgo’s. He believes that it will be a staple in the study of urbanism within 5 to 10 years. “Change happens to be contagious,” he says. He, obviously, means it with regards to how cities morph over time–but it seems just as applicable to the complete spread of machine learning, too.