US researchers have used big-data analysis of mobile phone data to build a model of urban travel patterns which provides timelier and more accurate data than commuter surveys.
In an article published in the Proceedings of the National Academy of Sciences, researchers from MIT and Ford Motor Company describe a new computational system that infers urban mobility patterns from mobile phone location data.
Typically, city planners rely on surveys of residents’ travel habits to understand how people move through their cities on foot, in cars and on public transport. These surveys are used when making decisions about infrastructure development and resource allocation.
However, conducting surveys and analysing their results is costly and time consuming. What’s more, they only cover a fraction of a city’s population.
For the new study, the researchers assembled a model of urban mobility patterns using six weeks of mobile phone location data from residents of the Boston area.
They then compared this model to the one currently used by Boston’s metropolitan planning organisation. The two models accorded very well, MIT reported.
“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,” explained Marta Gonzalez, an associate professor of civil and environmental engineering at MIT and senior author of 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.”