Analytics tool predicts the traffic for Bay Area drivers
Connecting state and local government leaders
The IBM Traffic Prediction Tool analyzes traffic data from sensors in roads, toll booths, bridges and intersections and combines it with GPS data from drivers' cell phones.
The California Department of Transportation (Caltrans), in conjunction with the California Center for Innovative Transportation (CCIT), a research institute at the University of California-Berkeley, and IBM Research, unveiled a new predictive modeling and analytic tool to help San Francisco Bay area officials better plan and manage traffic flows, as well as help commuters avoid traffic jams.
The IBM Traffic Prediction Tool (TPT), part of the Bay Area’s Smarter Traveler Research Initiative, collects and analyzes traffic data from sensors in roads, toll booths, bridges and intersections and combines the information with GPS location data from participating individuals’ cell phones.
Related story:
Can app predict future traffic jams?
It compiles a commuter’s typical routes and uses the data to provide individuals with personalized travel recommendations to help them plan and share alternate routes - even before congestion is reported. Commuters receive alerts via e-mail or text message before their trip begins, including alerts on highways, rail lines and roads.
“As the number of cars and drivers in the Bay Area continue to grow, so too has road traffic," Greg Larson, chief of the Office of Traffic Operations Research for Caltrans said in an announcement by IBM. "However, it’s unrealistic to think we can solve this congestion problem simply by adding more lanes to roadways, so we need to proactively address these problems before they pile up,” he added.
By better understanding and predicting traffic flows, transportation officials will be able to proactively manage and optimize transportation systems, including improving traffic signal timing and ramp metering. Officials can also recommend better routes, predict whether or not a train will be on time, or train station parking availability.
Alerts will be sent to commuters only if there is something potentially problematic, such as an accident or construction, to avoid overwhelming people with alerts, said Stefan Nusser, functional manager of IBM's Almaden Services Research in a CNET article.
The tool is currently in trials and is not meant to be accessible while driving to avoid potential incidents because of cell phone usage behind the wheel, he added.