Official US Government Icon

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure Site Icon

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

USDOT Announces Safety Data Initiative, Pilot Programs to Apply Innovative Analysis to Transportation Safety

Monday, January 8, 2018

Multi-dimensional models of the transportation system will provide insights that will help improve safety on our highways

WASHINGTON – The U. S. Department of Transportation (USDOT) is launching a multi-modal initiative, including two pilot programs to modernize its data analysis and integrate its traditional datasets with new “big data” sources to gain insights into transportation safety. 

“Advances in data science have the potential to transform the Department’s approach to safety research and provide insights that can help improve highway safety,” said U.S. Department of Transportation Secretary Elaine L. Chao.

Under Secretary of Transportation for Policy Derek Kan announced the initiative at the Transportation Research Board Conference on January 8th.

One pilot project will integrate established data on known crashes and highway design with anonymous data from GPS-enabled devices that provides prevailing speeds at 5-minute intervals across the entire National Highway System. For the first time, the Department will be able to look directly at prevailing operating speeds at a large scale to see how speed and speed differentials interact with roadway characteristics to influence the likelihood of crashes.  Every year speeding is a contributing factor in traffic fatalities, and in 2016 10,111 roadway deaths involved speed.  The pilot will also look at the role of speed in rural incidents.

The second pilot project will integrate traffic crash data with data from the crowd-sourced app Waze on traffic hazards and conditions. This initiative will examine the feasibility of using this new crowd-sourcing application to provide a reliable, timely indicator of reportable traffic crashes, and estimate crash risk based on Waze-reported hazards.

Together, these pilot projects represent a new approach to data analysis that will seek to augment traditional data sources with new data that can be collected and analyzed much more quickly. This approach will create new multi-dimensional models of the transportation system. The initial focus of the effort is on gaining insights that will help drive down highway fatalities.