Knowledge-Based Machine Learning for Freeway COVID-19 Traffic Impact Analysis and Traffic Incident Management
The U.S. Department of Transportation (USDOT) needs to respond quickly and adapt to the coronavirus (COVID-19) to ensure continuation of critical infrastructure support and relief for the American people. Since early March 2020, the COVID-19 pandemic has had significant impact on traffic across the United States. It is clear to see that traffic patterns, traffic demands, and duration alter with COVID status. Therefore, there is a critical research need to study the impact of COVID on traffic patterns and to analyze the relationships among traffic demand patterns, daily confirmed cases/deaths, state policies, public perceptions, etc. In this research, the authors investigate the impact of COVID-19 on traffic safety in different stages, focusing on Salt Lake County, Utah. Statistical methods are employed to determine if there are any differences in the effects of the pandemic. Further, the effect of COVID-19 on traffic patterns in Salt Lake County and Utah County from January 2019 to July 2021 was analyzed. Different vehicle miles traveled (VMT) patterns in the pre-pandemic stage, early stage of the pandemic, and late stage of the pandemic are identified. Finally, a knowledge-based traffic prediction model utilizing an innovative approach that integrates machine learning with graph theory is proposed to forecast traffic patterns in the near future.
- Record URL:
- Record URL:
- Summary URL:
-
Supplemental Notes:
- This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
-
Corporate Authors:
North Dakota State University, Fargo
Fargo, ND United States 58105University of Utah, Salt Lake City
Salt Lake City, UT United States North Dakota State University
Fargo, ND United States 58108Office of the Assistant Secretary for Research and Technology
University Transportation Centers Program
Department of Transportation
Washington, DC United States 20590 -
Authors:
- Lu, Pan
- Yang, Xianfeng (Terry)
- Gong, Yaobang
- Publication Date: 2023-8
Language
- English
Media Info
- Media Type: Digital/other
- Edition: Final Report
- Features: Appendices; Figures; Maps; References; Tables;
- Pagination: 54p
Subject/Index Terms
- TRT Terms: COVID-19; Machine learning; Traffic forecasting; Traffic safety; Traffic volume; Travel demand; Vehicle miles of travel
- Geographic Terms: Salt Lake City (Utah)
- Subject Areas: Highways; Operations and Traffic Management; Planning and Forecasting; Safety and Human Factors;
Filing Info
- Accession Number: 01895542
- Record Type: Publication
- Report/Paper Numbers: MPC 23-502
- Contract Numbers: MPC-657
- Files: UTC, NTL, TRIS, ATRI, USDOT
- Created Date: Oct 6 2023 1:40PM