IBM, the California Department of Transportation and the University of California Berkeley's California Center for Innovative Transportation announced on Wednesday a collaboration on real-time predictive traffic modeling for the Bay Area.
The goal: help transportation agencies better understand and manage traffic flow, and help commuters avoid congestion before they leave the driveway.
At the heart of the project is an IBM predictive modeling tool that:
The latter point is a big one. We've discussed the growth of urban areas in the U.S. extensively here on SmartPlanet; with that population growth and increased density comes more traffic headaches.
Few areas of the country know this reality more than the San Francisco Bay Area.
"It's unrealistic to think we can solve this congestion problem simply by adding more lanes to roadways," Caltrans traffic operations research chief Greg Larson said in a statement. "So we need to proactively address these problems before they pile up."
It's not just dealing with the overall congestion trend, either. Officials plan to use the real-time aspect of the modeling tool to quickly manage incidents such as crashes or construction.
Here's how it works for the consumer: the system collects and analyzes traffic data generated from existing sensors in roads, toll booths, bridges and intersections. It then combines that data with locational data from the GPS sensor in your mobile phone to mash-up your commute with existing congestion, then delivers recommendations directly to you.
The system will also help transportation officials improve traffic congestion ahead of traffic signal timing improvements, ramp metering and route planning projects.
IBM says it's trying to take the guesswork out of commuting, but it goes beyond that. Congestion is a hamper on a city's economy -- not to mention its carbon footprint. An increase in the capacity of existing infrastructure results in real savings.
Here's a look in a video:
This post was originally published on Smartplanet.com