Current crash prediction methods—such as those in the AASHTO Highway Safety Manual (HSM)—consist of safety performance functions (SPF), crash modification factors (CMF), and severity distribution functions (SDF). These tools use annual average daily traffic (AADT) data along with geometric and operational characteristics to predict annual average crash frequency of roadway sites. While these models have statistical merit, they do not allow users to accurately predict crashes for variable, short-term periods (e.g., peak periods, special events). This can be an issue for agencies wanting to assess the safety impacts of temporary works zones or time-of-day capacity changes (e.g., lane configuration or speed limit). The existing annual prediction convention also limits the models’ ability to quantify the effects of variables that fluctuate throughout the day (e.g., operating speeds, or operating speed variance). State departments of transportation require the ability to more accurately assess daily or hourly changes that could affect crash outcomes. There is a need for research to explore new data, revised aggregations, and newer statistical methods to effectively model highway safety on a daily, hourly, or other short-term basis.
The objectives of this research are to: (1) develop short-term crash prediction models to estimate the safety performance of roadways. Consideration should be given to specific geometric, operational, and exposure characteristics (e.g., detours, variable speed limits), and routes that experience short-term capacity changes (e.g., hard shoulder running, reversible lanes). (2) Identify explanatory variables measured over short durations. Include more precise measures of exposure other than AADT (e.g., peak hour volume, special event volume), and factors such as speed (including speed variability) to help predict crashes for varied periods of time. (3) Develop an implementation tool suitable for practitioner use.
Task 1. Conduct a critical literature review and identify available national and regional databases, lessons learned, successful practices, gaps, and, challenges.
Task 2. Determine the feasibility of utilizing databases identified in Task 1 and/or identify new data sources (e.g., the use of real-time traffic monitoring data) to develop and prioritize use case scenarios.
Task 3. Develop a plan for data collection. Consideration should be given to identifying what the appropriate measures of exposure, explanatory variables, appropriate modeling tools (statistical analysis and/or machine learning models), model limitations, and other necessary factors that will assist in developing and implementing the models and interpreting results.
Task 4. Prepare an interim report that documents the work completed in Tasks 1, 2, and 3. Include a detailed work plan for the work anticipated in Phase II.
Task 5. Collect, integrate, and verify the usability of the data identified in Task 2.
Task 6. Develop validated crash prediction models for the prioritized use case scenarios.
Task 7. Develop the tool and user-friendly practitioner’s guide with feedback from a small NCHRP-approved expert group.
Task 8. Develop training materials, marketing, and outreach strategy that will identify four state transportation agencies that will be included in the sample case scenarios.
Task 9. Prepare a second interim report that documents the work completed in Tasks 5 through 8.
Task 10. Test the developed models and tool(s) using the selected strategy developed in Task 8. Conduct demonstration and training with the identified states.
Task 11. Conduct webinar suitable for a broad range of stakeholders.
Task 12. Develop the final deliverables.