3B.5 Route Travel Time Forecasting Challenges and Solutions

Tuesday, 24 January 2017: 11:30 AM
611 (Washington State Convention Center )
Thomas Brummet, NCAR, Boulder, CO; and G. Weiner, S. Linden, W. Petzke, A. Anderson, and P. McCarthy

Accurate travel time forecasts are not only helpful for commuters, but are necessary for state transportation departments to support road management and traffic mitigation.  Route specific travel time forecasts are dependent on a wide variety of factors including daily traffic patterns, road construction, accidents, special events, and hazardous weather.  In order to determine the impact of winter weather on travel times, the Colorado Department of Transportation (CDOT), requested the National Center for Atmospheric Research (NCAR) to develop a travel time forecasting system to provide route specific travel time forecasts out to 24 hours for the I-70 corridor between DIA and Vail.

In response to this request, NCAR applied machine learning algorithms to predict travel times on road segments for two minute time intervals.  The machine learning algorithms were applied to a database consisting of weather data including temperature and precipitation observations from nearby MADIS stations in conjunction with average travel time observations in order to create route-specific forecasting models.  The forecasting models were then used to produce 15-minute travel time forecasts over the next hour, and then hourly forecasts out to 24 hours.  The road segment travel times were then combined to create travel times for the individual routes.  Here the individual routes range from 1 mile up to 116 miles in length and consist of one or more individual road segments.

This presentation will outline a number of the many challenges that were faced in developing and running the forecasting system, from quality controlling historical data to handling changes in traffic patterns.  It will discuss the methodology used to address these challenges as well as the algorithm for combining the segment specific travel time forecasts into a total route forecast.  In concluding the presentation, performance results and ideas for future development will be discussed.

- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner