Predictive Analytics for Traffic Management on I-270 in St. Louis

Safety Champion

Contact Photo
chief safety and operations officer becky allmeroth
Becky Allmeroth
Chief Safety and Operations Officer
Contact Info

Missouri Department of Transportation

105 W. Capitol Ave.

Jefferson City, MO 65102

Phone: (573)-751-2803

Email  |  Bio

Project Manager

Contact Photo
Ploisongsaeng Portrait
Ploisongsaeng Intaratip
Senior Traffic Studies Specialist
St. Louis District
Contact Info


Phone: (314) 315-7481



Purpose of the Project:

One of MoDOT’s major areas of focus is improving the safety of roadways. There are many factors that can cause crashes, ranging from driver behavior to roadway geometry to weather conditions. MoDOT has applied many different engineering and behavioral strategies in pursuit of safety, such as public outreach to educate younger drivers, promotion of safety campaigns, analyzing fatal and serious injury crashes to perform systemic safety improvements, and road safety audits. Despite these efforts, crashes still happen. Even with all of the roadway and crash data available to MoDOT it is difficult to predict future crash locations. MoDOT and other emergency responders must react to crashes as they happen and respond as quickly as possible from their current locations.

Predictive analytics is the integration of real-time and historical data sources into a single platform, frequently processed with the use of artificial intelligence or machine learning, for analysis and decision making in the near-term. An active construction project presents a challenge for traditional means of crash prediction due to the frequently changing roadway conditions. A predictive analytics engine can process and react to new data quickly to spot trends, allowing it to identify the circumstances which can lead to crashes before they occur. MoDOT is the first state transportation department in the country to focus the use of this tool in a heavy construction area with the pilot implementation on the I-270 Project in the St. Louis District.

The MoDOT predictive analytics pilot will provide the ability to predict high crash risk areas up to 24 hours in the future. This will help MoDOT to better monitor potential high-risk crash areas and position its Emergency Response vehicles to be proactive in responding to incidents. It will also improve safety, resource efficiencies and response times to crashes.

Predictive Analytics – Starting in August 2021, the crash prediction and incident detection algorithms were evaluated for their accuracy every quarter. The crash prediction algorithm will be evaluated only for AM (6-9am) and PM (3-6pm) peak hours. The incident identification algorithm will be evaluated for fatal and serious injury crashes only. The results are based on crash data captured by Transportation Management Center operators in MoDOT’s ATMS software, so it is likely that some crashes on Interstates went unrecorded and are not included in the data set.

The project scope was adjusted to get higher accuracy on both algorithms by including more connected vehicle data feeds, installing 74 static cameras to collect traffic data, and pursuing St. Louis County 911 CAD data. Please see below for the integration status of each data source:

  1. Wejo CV data – Live on March 7, 2022
  2. Traffic Vision – Live on April 18, 2022
  3. HaaS – Live on June 2022
  4. Volvo – Live on August 2, 2022
  5. iCone – Live on August 16, 2022
  6. 74 static cameras – Installed by September 9, 2022, and dashboard training on October 3, 2022
  7. Otonomo – Live on September 21, 2022
  8. St. Louis County CAD – in progress
  9. Surfsight – in progress
  10. Dash Cam – Live on August 10, 2023

Figure 1 shows the number of peak hour crashes predicted compared by month and the results for the visible and nonvisible crash risk location predictions for July. Visible crash risk locations are locations where the algorithm predicts an elevated risk of a crash occurring and displays them on the map. Nonvisible crash risk locations are locations where the algorithm predicts an elevated risk of a crash occurring and does not display them on the map. The crash risk location prediction algorithm can predict anywhere from 1 location to about 70 locations per 3-hour period. The purpose of adding more crash risk locations per period is to experiment and evaluate the performance of crash risk locations after the change.  

Figure 1: Number of peak hour crashes predicted by month (peak hour: 6-9 am and 3-6 pm)

In order to evaluate the effectiveness of the algorithm, an analysis was done to identify how many predicted crash-risk locations experienced crashes during the prediction timeframe. In July 2023, the results showed visible crash risk locations were decreased compared to April. These results fluctuated based on the experiment with the algorithm settings. MoDOT and Rekor are continuing to work closely together to improve of the accuracy of the results. In addition, Rekor released crash risk location prediction version 2 on August 29, 2023. The evaluation of the new crash risk location prediction will be present in the I-270 Predictive Layered Operations Initiative final report.

Table 1 shows the results for the incident identification algorithm for fatal and serious injury crashes. There were 320 total matching crashes between the ATMS and Rekor systems that could be used for the evaluation in July 2023. The algorithm was rated against existing methods based on whether Rekor detected an incident prior to all other tools including police radio, Waze, and CCTV monitoring, among others. July 2023 results showed that 49.1% of incidents were first identified by Rekor, which is increased from the April 2023. The percentage of incidents identified simultaneously were slightly decreased to 8.1%.

 Advanced Video Analytics – Video analytics were fully operating as of April 2022. July 2023 results showed a total of 922 incidents detected by TrafficVision. Twenty eight  out of 922 incidents were pedestrians, which is about 3% of the total incidents. The top 3 incident types are stopped vehicle/object (40%), congestion (34%), and slow speeds (23%).

Table 2 shows the results for the advanced video analytics performance. The percentage of false incidents for July increased significantly compared to April results due to an impact to a camera setting when MoDOT switched to the new ATMS provider in March 2023. The category “Unable to Verify” includes alerts that could not be verified due to speed of traffic, clarity of video, weather interference, or other conditions.

IMRCP – The platform was fully operational in February 2022. No updates at this time.

Interview Results – In February 2023, I-270 PLOI project team interviewed 6 TMC operators, 3 ER operators, and 4 managers on the performance of the Rekor and TrafficVision. Table 3 shows the results from the interviews separated by group. The I-270 PLOI project team is planning to conduct a second round of interviews in Fall 2023.

Table 3: February 2023 Interview Results




TMC Operators

  • Rekor and TrafficVision identify unknown incidents accurately and quickly.
  • Rekor and Traffic Vision help pinpoint location of incidents.
  • Multiple data sources feeding into the platforms creates duplicate incident listings which create additional work.

ER Operators

  • Rekor gives operators map of incidents.
  • Rekor reduces radio traffic.
  • GPS location issues.
  • MoDOT safety protocols prevent full use.

MoDOT Supervisors and Managers

  • Rekor and TrafficVision consolidated information.
  • Both platforms create historical data.
  • Both platforms provide organizational experience.
  • Rekor was not user ready when it first deployed.
  • Crash risk location prediction accuracy.