New software program predicts traffic jams

New Scientist : A new system in San Francisco not only informs drivers of current traffic conditions but also predicts congestion up to 40 minutes into the future. The initiative is a joint project of IBM, the California Department of Transportation, and the California Center for Innovative Transportation (CCIT) at the University of California, Berkeley. The Smarter Traveler Research Initiative combines real-time traffic data with past traffic patterns to predict backups. “The edge of a traffic jam propagates like a shock wave in a fluid,” says Alexandre Bayen at CCIT, and thus follows predictable patterns. The Traffic Prediction Tool software draws data from existing “inductive loop” sensors built into roadways and from the GPS on participants’ smartphones to learn their preferred travel times and routes. Drivers can receive e-mails or text messages that apprise them of traffic conditions on their regular commute and recommend alternative routes. Before expanding the service to commuters worldwide, however, the researchers say it needs more work: The software needs to anticipate the problems that could ensue if too many drivers suddenly change their route and create congestion somewhere else.