Predicting Traffic Jams


IBM is developing a new traffic analysis system that can predict where traffic jams will occur before the driver finds him or herself stuck in one.  The system uses predictive modeling, incorporating data from road sensors, weather conditions, historical traffic data, and real-time GPS data from taxis.  Road tested in Singapore, Finland, and New Jersey, the system has been able to accurately predict traffic volume 85% to 93% and travel speeds 87% to 95% of the time.  The modeling system can predict the occurrence of a traffic jam one hour before it occurs.

Read more: Predictive Modeling Warns Drivers One Hour before Jams Occur


Support More Content on GIS Lounge

Advertising only covers a portion of the cost of running this site. Would you like to see more daily content about GIS and geospatial trends on GIS Lounge? All funds received through Ko-Fi will go directly towards hiring more contributors to write for GIS Lounge.

Like this article and want more?

Enter your email to receive the weekly GIS Lounge newsletter: