Traffic congestion 'temperature' could forecast delays

December 08, 1999

The Weather Channel has brought to forecasting weather what a Georgia Institute of Technology researcher hopes to bring to predicting traffic congestion.

People plan their days according to the weather forecast, but they can't do that with traffic -- at least not quite yet, said Dr. John Leonard, an associate professor in the School of Civil and Environmental Engineering.

Leonard is developing a cutting-edge traffic flow model that analyzes a variety of historical data and a host of variables to predict the next day's traffic conditions. He calls it a traffic congestion "temperature." The model will also estimate current travel times from point to point.

"People need a simple-to-understand number -- even if it doesn't have a physical meaning -- to represent traffic congestion," Leonard said. "We need to publicize it daily so people start to develop a personal understanding of congestion and plan accordingly."

Leonard is creating his model using the past two years' data from traffic surveillance systems -- such as the Georgia Department of Transportation's 300-plus video cameras installed on freeways in metro Atlanta. The model also incorporates data from commonly used loop detectors on roadways.

One byproduct of Leonard's research is a graphic representation of congestion. For each day of data, he is creating "star" diagrams that graphically show travel time estimates from various points of origin to any of the five points on the "star" created from a map of the city's major highways. Then he will examine the data for trends and try to correlate them with variables such as special events, hotel occupancy, time of day, holidays, schools in session, weather and, of course, vehicle accidents. An analysis of this information, combined with current traffic conditions, would then yield a prediction of traffic congestion for the next 24 hours.

In Atlanta, the points of origin would be major workplaces or centers of activity, such as Tech, Coca-Cola, the airport and malls. The travel time estimates on Atlanta's "star" diagram would go to: Interstate 285 at I-75 north; I-285 at I-85 north; I- 285 at I-75 south of the city; I-285 at I-85 south of the city; and the airport.

Leonard believes if people became familiar with a traffic "temperature," they would change their travel behavior and ultimately lessen traffic congestion.

"Many people have the flexibility to plan their trips according to traffic congestion," Leonard said. "With this sort of pre-trip information, people could decide whether to leave now or wait 10 minutes. . . . This could spread the peaks out a little and improve travel times for everybody."

Leonard sees a particular benefit for people who make a lot of discretionary trips and a benefit to couriers who might be able to reschedule or reroute deliveries.

Publicizing the traffic congestion index will be key to its having the intended effect. Leonard envisions freeway message board, radio, television and Web site distribution. In fact, he has an early prototype for Atlanta available online at .

"We're not ready for prime time yet," Leonard said. "We have to work on getting the prediction close. I want to be accurate 90 to 100 percent of the time."

Besides the obvious short-term benefits of a traffic congestion index, long-term benefits would include better traffic planning for the future. This information should also be integrated with ozone pollution forecasting, work that is also ongoing at Georgia Tech, he added.

Leonard's research is now funded internally at Georgia Tech. He has discussed the work with officials at the Georgia DOT, and they are providing historical data. He also hopes to capture the interest of the newly created Georgia Regional Transportation Authority (GRTA). Leonard believes the traffic "temperature" model would fit GRTA's plans for congestion indicators.

Full implementation of the traffic congestion index is probably several years away, Leonard said. Though Atlanta will be the testbed for the index system, it could be implemented anywhere.
For technical information, contact:
Dr. John Leonard, 404-894-2360
Web Site:

Georgia Institute of Technology

Related Data Articles from Brightsurf:

Keep the data coming
A continuous data supply ensures data-intensive simulations can run at maximum speed.

Astronomers are bulging with data
For the first time, over 250 million stars in our galaxy's bulge have been surveyed in near-ultraviolet, optical, and near-infrared light, opening the door for astronomers to reexamine key questions about the Milky Way's formation and history.

Novel method for measuring spatial dependencies turns less data into more data
Researcher makes 'little data' act big through, the application of mathematical techniques normally used for time-series, to spatial processes.

Ups and downs in COVID-19 data may be caused by data reporting practices
As data accumulates on COVID-19 cases and deaths, researchers have observed patterns of peaks and valleys that repeat on a near-weekly basis.

Data centers use less energy than you think
Using the most detailed model to date of global data center energy use, researchers found that massive efficiency gains by data centers have kept energy use roughly flat over the past decade.

Storing data in music
Researchers at ETH Zurich have developed a technique for embedding data in music and transmitting it to a smartphone.

Life data economics: calling for new models to assess the value of human data
After the collapse of the blockchain bubble a number of research organisations are developing platforms to enable individual ownership of life data and establish the data valuation and pricing models.

Geoscience data group urges all scientific disciplines to make data open and accessible
Institutions, science funders, data repositories, publishers, researchers and scientific societies from all scientific disciplines must work together to ensure all scientific data are easy to find, access and use, according to a new commentary in Nature by members of the Enabling FAIR Data Steering Committee.

Democratizing data science
MIT researchers are hoping to advance the democratization of data science with a new tool for nonstatisticians that automatically generates models for analyzing raw data.

Getting the most out of atmospheric data analysis
An international team including researchers from Kanazawa University used a new approach to analyze an atmospheric data set spanning 18 years for the investigation of new-particle formation.

Read More: Data News and Data Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to