Baldwin, M. E., Burris, K. D., & Elmore, K. L. (2018). Automated estimation of winter driving conditions (Joint Transportation Research Program Publication No. FHWA/IN/JTRP-2018/22). West Lafayette, IN: Purdue University. https://doi.org/10.5703/1288284316867
There is great potential for improvements in traveler safety and satisfaction as new sources of information are incorporated into advanced analytics and prediction systems. It is critical for transportation agencies to be able to monitor weather conditions in real-time as well as over the long-term for purposes of maintenance, planning, and performance evaluation. Travelers also use this information to plan their routes, make decisions on timing, and improve their awareness of potential hazards. A machine learning model was developed in this project to automatically estimate winter driving conditions in real-time using weather information as input. This system can provide rapid updates of changing conditions and help reduce the effort required to report driving conditions during intense winter storms. The system performed well in an experimental evaluation during the 2017-18 season. Seasonal analyses of winter precipitation that incorporated crowd-sourced observations were also generated and displayed significant differences from previous research.
road weather, machine learning, crowd-sourced observations
Joint Transportation Research Program
Indiana Department of Transportation
West Lafayette, Indiana
Date of this Version