Validate Field Devices and Data Streams Before Initiating Artificial Intelligence-Based Decision Support System Model Development.
Lessons Drawn from a Deployed Artificial Intelligence-Based Decision Support System (AI-DSS) on the I-24 Corridor in Tennessee.
Nashville, Tennessee, United States
Murfreesboro
ATCMTD Final Report for the TDOT Artificial Intelligence-Based Decision Support System (DSS)
Summary Information
The Interstate 24 (I-24) corridor between Nashville and Murfreesboro, Tennessee, has experienced persistent congestion and safety challenges, creating a need for operational strategies that could improve corridor performance. To address these challenges, the Tennessee Department of Transportation (TDOT) and its partner agencies implemented intelligent transportation systems (ITS) integrated corridor management (ICM) strategies to enhance safety and efficiency along this corridor. Funded under the Advanced Transportation and Congestion Management Technologies Deployment Initiative (ATCMTD) grant program in 2021, TDOT deployed an Artificial Intelligence-Based Decision Support System (AI-DSS) to support real-time traffic management. Compared with microsimulation-based decision support systems (DSS), the AI-DSS was designed to be more economical, efficient, and transferable. The system utilized various transportation management technologies including variable Speed Limit (VSL) signs, Lane Control Signs (LCS), Dynamic Message Signs (DMS), video detection for emergency pull-offs, upgraded and connected traffic signals, new closed-circuit television (CCTV) cameras, and Radar Detection Systems (RDS). The AI-DSS gathers traffic and incident data from field monitoring devices and TDOT’s SmartWay Central Software, analyzes corridor conditions in real time, and provides recommended actions to the Transportation Management Center (TMC). These actions included posting VSLs, sharing traveler information, supporting lane-control operations, and recommending traffic signal timing changes. The deployment extended along I-24 between the I-440 and I-840 interchanges, where TDOT constructed 67 overhead gantries placed approximately every half mile in each direction.
Key lessons from the I-24 AI-DSS deployment are summarized below.
- Validate field devices and data before initiating AI-Based Decision Support System model development. Developing data-driven models before field devices and data streams are fully deployed and validating can be challenging. The project found that AI model development should ideally begin only after data pipelines and field devices are fully operational and producing reliable, consistent data. It can also rely on existing or legacy datasets to establish baseline information. In addition, ensuring data readiness and quality control prior to baseline collection is essential for reliable system performance and evaluation.
- Early deployment of dashboards and visualization tools is beneficial. Even rudimentary dashboards were found to be highly valuable for monitoring system performance, supporting operational decision-making, and facilitating communication among project partners. It’s beneficial to implement these tools early in the project lifecycle and refine them iteratively.
- Project delivery structure strongly influences implementation efficiency in complex ITS deployments. Alternative delivery methods (e.g., integrated project delivery) should be considered for future similar projects as they can improve coordination among stakeholders, streamline decision-making, and enhance overall system integration outcomes in large-scale, multi-agency deployments.
