skip to main content

T3e Webinar Overview

Predictive Analytics for Optimal Decisions: Examples in Real-time Traffic Management and Mobility Services

Date: Thursday September 30, 2021
Time: 1 PM–2:15 PM ET
Cost: All T3 webinars are free of charge.
PDH: 1.5 | View PDH Policy

This event took place on September 30. The archive will be available in October.

T3 and T3e Webinars are brought to you by the Intelligent Transportation Systems (ITS) Professional Capacity Building (PCB) Program of the U.S. Department of Transportation’s (USDOT) ITS Joint Program Office (JPO). References in this webinar to any specific commercial products, processes, or services, or the use of any trade, firm, or corporation name is for the information and convenience of the public, and does not constitute endorsement, recommendation, or favoring by the USDOT.


The U.S. Department of Transportation (USDOT) is hosting a series of webinars on emerging academic research in various aspects of intelligent transportation systems (ITS) or smart communities. This 60-minute webinar will present work by the Mobility Data Analytics Center (MAC) at Carnegie Mellon University (CMU) that develops comprehensive solutions for managing transportation infrastructure and mobility services, with a focus on applying artificial intelligence (AI) techniques in transportation domain leveraging multisource large-scale data. The research is funded by USDOT’s Mobility21, a national University Transportation Center, National Science Foundation, and Traffic21 Institute at CMU.

Target Audience

The target audience includes State Departments of Transportation, metropolitan planning organizations (MPOs), transit agencies, and other agencies that support traffic operations and multimodal mobility services.

Learning Objectives

The objectives of this webinar are for the audience to learn about:

  • Real-time predictive analytics for non-recurrent traffic management
    • Fuse and understand multisource high-granular data
    • Automate an optimal decision-making process using data and artificial intelligence (AI)
    • Make decisions proactively and predictively, rather than reactively
  • Design, planning, and operation of first-mile/last-mile (FMLM) mobility services to improve accessibility
    • Integrate FMLM service with public transit and ride-hailing service
    • Provide strategic design of on-demand, stopping, fleet size/seating, and coordination with other modes
    • Use multisource data for predictive demand matching and routing
    • Analyze cost/benefits for riders and public agencies


Sean Qian, Henry Posner, Anne Molloy, and Robert and Christine Pietrandrea Associate Professor, (joint appointment at the Department of Civil and Environmental Engineering (major) and Heinz College of Information Systems and Public Policy (minor)), Carnegie Mellon University
Sean Qian Mr. Qian directs the Mobility Data Analytics Center (MAC) at Carnegie Mellon University (CMU). Mr. Qian’s research interest lies in large-scale dynamic network modeling and large-scale data analytics for multimodal transportation systems, in the development of intelligent transportation systems (ITS) and in understanding infrastructure system interdependency. His research has been supported by a number of public agencies and private firms, including the National Science Foundation (NSF), U.S. Department of Energy (DOE), USDOT, Pennsylvania Department of Transportation (PennDOT), Maryland Department of Transportation (MDOT), Pennsylvania Department of Community and Economic Development (DCED), IBM, Honda R&D, Benedum Foundation, and the Hillman Foundation. Sean was the recipient of the NSF CAREER award in 2018 and Greenshields Prize from the Transportation Research Board in 2017.


Weiran Yao, Research Assistant, Mobility Data Analytics Center, Carnegie Mellon University
Weiran Yao Mr. Yao is a PhD student in the Department of Civil and Environmental Engineering (CEE) at Carnegie Mellon University. Mr. Yao’s research focuses on developing physics-informed artificial intelligence/machine learning (ML) techniques for smart mobility and transportation network modeling and advanced data analytics for characterization, evaluation, and optimization of operation and management of large-scale transport systems.

Planned and unplanned incidents (e.g., hazardous weather conditions, accidents, local events, etc.) on highway networks can catastrophically impact mobility and safety. Traffic operators do not know which time and which strategy to engage to mitigate non-recurrent impacts, as well as how to incorporate ever-increasing traffic data. This research proposes to develop ML theories, models, and algorithms leveraging multisource data (speeds, weather, incidents, and crowdsourcing) to achieve two main goals: predict non-recurrent traffic conditions in large-scale networks at least 30 minutes ahead, and proactively recommend operational management strategies in real-time.

Rick Grahn, Research Assistant, Mobility Data Analytics Center, Carnegie Mellon University
Rick Grahn Mr. Grahn is a PhD student in the Department of Civil & Environmental Engineering at Carnegie Mellon University. His research analyzes the impacts of emerging technologies and modes on transportation systems. Most recently, his research has focused on the relationship between ride-hailing services (Uber/Lyft) and public transit. Rick is a registered professional engineer in the State of California.

Ride-hailing services, such as Uber and Lyft, have clear operational advantages (real-time analytics/optimization, vehicle supply distributed across time and space) compared to many small transit providers that can lead to improved performance at lower costs. This research explores a partnership between ride-hailing and public transit in the first-mile last-mile context. System performance and costs were quantified for different vehicle supply scenarios: (i) on-demand shuttles only; (ii) on-demand shuttles and ride hailing; and (iii) ride-hailing only.

↑ Return to top


Technical Assistance is available to Federal, State and local transportation agencies through:

ITS Peer Program - The ITS Peer-to-Peer Program puts you in touch with technical experts or experienced peers.

ITS Help Line - The ITS Help Line provides technical support by email or telephone at 866-367-7487.


go to twitter    go to Facebook    go to Instagram    go to Linkedin    go to YouTube    go to email