In making decisions about infrastructure development and resource allocation, city planners rely on models of how people move through their cities, on foot, in cars and on public transport; these models are largely based on surveys of residents’ travel habits. However, a new method of big-data analysis could give planners timelier, more accurate alternatives to commuter surveys.
As conducting surveys and analyzing their results is costly and time consuming, many cities may go more than a decade between studies. Furthermore, even a broad survey will cover only a tiny fraction of a city’s population. Researchers from the Massachusetts Institute of Technology (MIT) and Ford Motor Company are developing a new computational system that uses cellphone location data to infer urban mobility patterns. Applying the system to six weeks of data from residents of the Boston area, the researchers were able to quickly assemble the kind of model of urban mobility patterns that typically takes years to build. The system holds the promise of not only more accurate and timely data about urban mobility, but also the ability to quickly determine whether particular attempts to address cities’ transportation needs are working.
Previously, Boston had conducted an urban mobility survey in 1994 and another in 2010, but its current mobility model still uses the earlier data, as the information collected in 2010 is still being collated. Although the MIT researchers had access to much more data, from each of 1.92 million residents, it was less complete, as cellphone records report only the locations at which users place calls or access the internet. However, their algorithm was able to infer patterns of activity that recurred over the course of the six-week period by making a few probabilistic assumptions, based on location, time of day and other recurring patterns. The system then generalizes those probabilities across communities, on the basis of census data, and deduces cumulative traffic flows from the resulting probability map. To validate their new system, the researchers compared the model it generated with the model currently used by Boston’s planners, and the two models accorded very well.
“The great advantage of our framework is that it learns mobility features from a large number of users, without having to ask them directly about their mobility choices,” said Marta Gonza?lez, an associate professor of civil and environmental engineering at MIT and senior author on the paper. “Based on that, we create individual models to estimate complete daily trajectories of the vast majority of mobile-phone users. Likely, in time, we will see that this brings the comparative advantage of making urban transportation planning faster and smarter, and even allows directly communicating recommendations to device users.”
Another contributor to the research, Shan Jiang, from MIT’s Human Mobility and Networks Lab, noted, “In the USA, every metropolitan planning organization’s main job is to use surveys to derive the baseline model for predicting and forecasting travel demand to build infrastructure. Our method and model could be the next generation of tools to plan for the next generation of infrastructure.”
