Technical Research & Training

Services Provided: Artificial Intelligence, Travel Demand Modeling

Insight is part of a team that is pioneering an initiative with the Florida Department of Transportation’s Forecasting & Trends Office (FTO). The project is part of FDOT’s broader efforts to integrate innovative technologies into planning workflows to enhance model reliability, efficiency, and reproducibility. Specifically, Insight is supporting the development of an AI-driven run routine designed to automate and enhance the calibration and validation of travel demand models, beginning with the Florida Hurricane Evacuation Model, also known as TIME.

The primary objective of this task is to increase the accuracy and consistency of model outputs while minimizing manual intervention and the potential for human error. The project aims to deliver a deployable routine that incorporates artificial intelligence (AI) methodologies into the model calibration and validation process. Insight’s high-level contributions include AI application development, model calibration and validation automation, and system integration, ensuring compatibility with all district and statewide planning models used by FDOT.

Insight is currently developing guidance for implementing AI solutions and identifying the value of open source versus proprietary AI options. Subsequent efforts will focus on designing an AI-driven auto-calibration framework for trip distribution in the TIME model, incorporating optimization algorithms that adapt to shifts in behavior and infrastructure conditions. Further work involves drafting a comprehensive user manual, developing training materials, and leading webinars to facilitate statewide adoption. Insight also contributed to broader support activities such as data gathering, trend evaluation, meeting facilitation, and the development of materials for stakeholder communication. 

The work will culminate in the delivery of a complete AI-enhanced model run routine and associated documentation by the end of 2026. 

Services Provided: Travel Demand Forecasting, Forecast Accuracy, Model Components Monitoring

The Federal Highway Administration (FHWA) initiated the Improving Travel Demand Forecasting Accuracy research project to build on the findings of National Cooperative Highway Research Program (NCHRP) Report 934 and address the nationwide variability and limitations in forecasting practices. The primary objective was to develop guidance and practical tools to improve the reliability of travel demand forecasts, thereby enhancing the quality of transportation planning and investment decisions. Insight Transportation Consulting Inc. (Insight) is supporting FHWA by examining current practices, identifying gaps through interviews with six diverse transportation agencies, and developing two distinct forecasting accuracy toolkits tailored to the needs of both Metropolitan Planning Organizations (MPOs) and project-level forecasters. 

The study revealed that while some agencies occasionally assess forecast accuracy, particularly at the project level, systemic reviews are rare due to long forecast horizons, evolving data sources, and staff turnover. The toolkit for regional forecasters emphasizes the annual review of key model components—socio-economic/land use data, transportation supply, travel demand, congestion levels, travel patterns, macro-trends, and emerging mobility options—using contemporary data such as location-based services (LBS) and crowd-sourced traffic data. The toolkit for project-level forecasts provides a procedural framework for initial and follow-up accuracy assessments that are adaptable to each agency’s definitions and thresholds of accuracy. Each tool includes data sources, deviation thresholds, and sample methods to streamline implementation. 

Currently being piloted by selected agencies, the toolkits aim to institutionalize continuous validation and reasonable monitoring practices, bridging the gap between methodological rigor and practical application. Insight’s contributions will help FHWA, and participating agencies better understand how to translate complex forecasting dynamics into actionable monitoring strategies. These lessons will continue to inform the refinement of model frameworks and elevate the standard of practice for travel demand forecasting nationwide. 

Services Provided: Model Users Support, TransCAD Travel Demand Model Review   

Insight provided travel demand modeling and data analytics support to the Florida Department of Transportation District 5 (FDOT D5). The FDOT D5 released the Central Florida Regional Planning Model Version 7 (CFRPM 7), in early 2021. Currently, this model is used for virtually all PD&Es and traffic analyses in FDOT D5, Long Range Transportation Plans for all Metropolitan Planning Organizations (MPOs) in the district, and numerous other planning and traffic study applications led by local agencies. As of 2023, FDOT D5 had converted the Cube Voyager version of the model to TransCAD but needed to confirm that the CFRPM 7 TransCAD model is ready to be adopted as the model of record for all future studies.  

Insight assisted FDOT D5 in confirming that, if needed, the CFRPM 7 TransCAD model is ready to be adopted by all MPOs in the District and determined the level of effort needed to update the model documentation and training materials. Insight reviewed the CFRPM 7 TransCAD model codes, CFRPM 7 Description and Validation Reports, and identified areas of improvement.

During this period, Insight also provided on-call technical support to CFRPM 7 users. Users submitted issues via the dedicated support@cfrom.org help desk. Insight staff responded within four business hours, and issues were resolved within one business day.  

Services Provided: Statewide Technical Training, STOPS Modeling   

Insight developed, organized, and conducted a series of three comprehensive workshops on the Federal Transit Administration's (FTA) STOPS software for the Florida Department of Transportation’s (FDOT) Rail and Transit Office. These workshops aimed to educate participants on various aspects of STOPS and its applications in transportation planning and analysis. Two workshops were conducted in-person and one was conducted virtually. Over 100 people attended the three workshops.  

The workshops were structured to cover a wide range of topics related to STOPS, ensuring that participants gained a thorough understanding of its capabilities and practical implementation. The sessions included: "An Introduction to STOPS," "Applying STOPS for Capital Investment Grant (CIG) Projects," "Example Applications for CIG Projects," "Applying STOPS for Non-CIG Projects," "Developing a STOPS Model," "Maintaining Your STOPS Model," "Analyzing Results from STOPS," and "Communicating Results from STOPS."

The material was designed to cater to different target audiences. The morning sessions were specifically tailored for managers, providing a comprehensive overview of STOPS, its characteristics and example applications. These sessions emphasized the strategic and managerial aspects of utilizing STOPS for transportation planning and analysis. The afternoon sessions were more technically oriented, targeting individuals responsible for implementing and maintaining STOPS models. These sessions delved into the practical aspects of applying STOPS, including model development, maintenance, and analysis of results. Customizing the content ensured that participants could gain actionable insights and apply their knowledge effectively in their respective roles. 

Insight was responsible for developing the course materials, developing the course announcements, handling the registration process and all logistics, and providing all instructors.