Data Driven Urban Traffic Prediction for Winter Performance Measurements

Project status

Completed

Start date: 08/01/14
End date: 12/31/16

Researcher(s)

Principal investigator:

Co-principal investigator:

About the research

Prediction of traffic speed drop under severe weather in an urban setting is important in measuring the performance of winter highway maintenance programs in the city. This work is built on our previous and current work on point level modeling and prediction of traffic speed drops during weather for performance evaluation in rural areas.

INRIX and Wavetronix traffic data and limited weather information were used to develop models for detecting abnormal traffic patterns and predicting traffic speed and volume at any location on a network. Multivariate quantiles were estimated for the INRIX observations, and the INRIX data were compared with the estimated quantiles to identify abnormal traffic patterns in both space and time.

An online interactive app was developed to visualize the results and inform decisions about winter maintenance. A dynamic Bayesian model was implemented at two Wavetronix sensor locations where weather information was available, with the corresponding median curve as the baseline.

The fitting results were satisfactory. The INRIX data’s spatial structure was explored, and curve Kriging was used to predict traffic speed and volume at any location. The prediction method worked well.

Publications

Report: Improving Estimates of Real-Time Traffic Speeds During Weather Events for Winter Maintenance Performance Measurement (2.50 mb pdf) April 2017

Sponsor(s)/partner(s)

Sponsor(s):

  • Iowa Department of Transportation
  • Midwest Transportation Center
  • USDOT/OST-R