Solving the mobility puzzle: Portland tests analysis tool based on cellphone data
Connecting state and local government leaders
The Replica technology takes de-identified location data from cellphones and pulls it into a dashboard that shows how, when, where and why people actually move around the city.
Transportation officials in the Portland, Ore., will soon have access to data on movements of residents, thanks to technology that takes de-identified location data from cellphones and pulls it into a dashboard that shows how people actually move around the city.
Replica mobility software pulls data from mobile app publishers, mobile location data aggregators and telecommunications operators, according to a report in GeekWire. The goal is to learn how, when, where and why people move around a city. The software was developed by Sidewalk Labs, a subsidiary of Alphabet, Google’s parent company.
Replica will provide transportation planners with travel metrics that currently are difficult to gather and maintain, including the total number of people on a highway or local street, whether they're driving, using public transit, biking or walking, and where they're headed – to work, shopping or school, for example. The city will get updates every three months, giving it the ability to spot trends that can inform future planning decisions.
The data Replica starts with has already been de-identified, according to a 2018 blog on the company's website. Travel behavior models are created using data from about 5% of the population help understand when, why and how people travel. The model is then matched to a synthetic population built from demographic data so that it is statistically representative of the full population. Computer simulations generate a week of replicated trip patterns across a city or metro area.
City officials will access a cloud-based platform where they can query and filter data based on the simulated population and create maps and charts to help them understand how streets, sidewalks and transit are used at different times of the day or by different types of people -- students vs. commuters, for example.
In December, Portland's city council voted to approve the agreement between the Bureau of Transportation, TriMet and the regional government Metro for a pilot. The city will test a dataset from Sidewalk Labs and, if satisfied, will begin paying 12 cents per resident to access the software for a year, GeekWire said.
Portland is one of eight U.S. cities, including Chicago and Kansas City, selected to test the tool.
NEXT STORY: Agencies warming up to AI