Estimating Highway Volumes Using Vehicle Probe Data - Proof of Concept: Preprint

Yi Hou, Stanley Young, Kaveh Sadabadi, Przemyslaw Sekula, Denise Markow

Research output: Contribution to conferencePaper


This paper examines the feasibility of using sampled commercial probe data in combination with validated continuous counter data to accurately estimate vehicle volume across the entire roadway network, for any hour during the year. Currently either real time or archived volume data for roadways at specific times are extremely sparse. Most volume data are average annual daily traffic (AADT) measures derived from the Highway Performance Monitoring System (HPMS). Although methods to factor the AADT to hourly averages for typical day of week exist, actual volume data is limited to a sparse collection of locations in which volumes are continuously recorded. This paper explores the use of commercial probe data to generate accurate volume measures that span the highway network providing ubiquitous coverage in space, and specific point-in-time measures for a specific date and time. The paper examines the need for the data, fundamental accuracy limitations based on a basic statistical model that take into account the sampling nature of probe data, and early results from a proof of concept exercise revealing the potential of probe type data calibrated with public continuous count data to meet end user expectations in terms of accuracy of volume estimates.
Original languageAmerican English
Number of pages12
StatePublished - 2018
EventITS World Congress 2017 - Montreal, Canada
Duration: 29 Oct 20172 Nov 2017


ConferenceITS World Congress 2017
CityMontreal, Canada

NREL Publication Number

  • NREL/CP-5400-70938


  • machine learning
  • neural networks
  • probe data
  • volume estimation


Dive into the research topics of 'Estimating Highway Volumes Using Vehicle Probe Data - Proof of Concept: Preprint'. Together they form a unique fingerprint.

Cite this