Developing a methodological framework to quantify the value of emerging data sources and AI-based products for systems operations and optimization.

Focus Area: Transportation Systems Management & Operations
Submitting On Behalf Of: TRB Committee on RTSMO
Urgency: Critical - High Priority
Cost: $500,000 - 749,000
Timeframe: 1 - 2 years
Type of Research: Full Research Project

Date Posted: Jul 10, 2024
Status: Not Funded

Research Description

Research Idea Description

Emerging transportation data sources and related AI products offer the potential to enhance and possibly transform Transportation Systems Management and Operations (TSMO). Several data vendors and software platforms already harness the power of new data through AI and provide solutions ranging from incident detection to intersection safety analysis. However, while new developments on the field of transportation data and AI hold enormous promise, transportation agencies often face challenges when assessing the value that new solutions provide, and the quality of the data generated through them. There is not a standardized approach to evaluate emerging methods and data sources, which is often difficult process because these often provide information that was not previously available to agencies. The new information is sometimes difficult to interpret and validate, which may limit its use and benefits.

Research Objectives

This effort will develop a taxonomy of emerging data sources and AI solutions that have the potential to enhance TSMO and propose a general evaluation framework that consider qualitative and quantitative aspects. The proposed research will also implement the framework to the analysis of one or more of the proposed categories of data/AI solutions.

Key Components:

The framework developed through this effort will include recommendations on metric definition and computation data workflows for various categories and hierarchies of data types and/or AI solutions (e.g. video-based detection methods, incident detection solutions). These metrics will be geared towards understanding: • Is the new data/information used • Is the new data/information accurate/reliable • Does the use of new data/information lead to a measurable improvement in relevant transportation system performance indicators • Does the use of new data/information lead to a measurable improvement in the day-to-day workflows of those using the data’

Expected Outcomes:

• Taxonomy of emerging data sources and AI products relevant to TSMO • Conceptual framework for the evaluation of emerging data sources and AI products based on proposed taxonomy • Proof-of-concept implementation of the framework to the assessment of one or more data source/AI solution using principles that facilitate replicability and transferability. o Detailed implementation guidelines

Potential Impact:

• Systematic approach to understand the benefits and value of emerging data sources and AI products  Improved strategic decision making concerning the adoption of new tools  Mechanism to provide feedback to data providers/AI vendors in order to improve the state of the practice • Enhanced use of advanced data tools and AI solutions

Additional Supporting Information

Submitted on behalf of the TRB Regional Transportation Management and Operations Committee subcommittee on Systems Operations and Optimization.

Submitted by: Thomas H. Jacobs, co-Chair, RTSMO Research Subcommittee

Submitted By: Thomas Jacobs; Center for Advanced Transportation Technology; 301-405-7328

Attachments

This idea has no attachments.

Comments

Join the Discussion

You can make your thoughts known by commenting, and by rating the idea and other comments. All you need to do is sign in, or register for an account with us!