T3e Webinar Overview

Advances in Modeling Transportation Supply and Demand: Coupling Activity-Based Travel Demand Modeling from Cellular Data with Agent-Based Modeling of Traveler Behavior and System Operations

View Webinar: link to this webinar's archive materials

Date:   Tuesday, December 12, 2017
Time:  1:00 PM – 2:00 PM ET
Cost:  All T3e webinars are free of charge
PDH:  1.0   View PDH Policy

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 (U.S. DOT) 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 U.S. DOT.


U.C. Berkeley’s Smart Cities Research Center and Lawrence Berkeley National Laboratory worked jointly to develop new capabilities to synthesize activity-based travel demand and to model the supply of the transportation system through agent-based modeling. They applied machine learning techniques to cellular data in order to extract statistically representative mobility patterns, allowing them to generate synthetic populations from any urban region. They have also developed next generation transportation simulation capabilities through the BEAM Framework for Behavior, Energy, Autonomy, and Mobility, a tool designed for scalability and to capture the increasingly connected and dynamic transportation system.

Target Audience

The target audience includes transportation researchers, modelers, planners, and policy-makers.

Learning Objectives

Upon completion of this webinar, the audience shall:


Dr. Alexei Pozdnukhov, Assistant Professor in Systems and Transportation Engineering at University of California, Berkeley

Dr. Alexei Pozdnukhov

Dr. Alexei Pozdnukhov holds a PhD in Computer Science from EPFL, Switzerland, following his research in machine learning methods and computer vision that he carried out at IDIAP Research Institute in Martigny, Switzerland. He then worked on remote sensing and spatial data mining at the University of Lausanne (UNIL). More recently, he held a position of a Science Foundation Ireland (SFI) Stokes Lecturer with the National Centre for Geocomputation (NCG).


Colin Sheppard, Transportation Scientific Engineering Associate at Berkeley Lab and PhD Candidate, UC Berkeley Transportation Engineering

Colin Sheppard

Colin Sheppard is a Transportation Scientific Engineering Associate at Lawrence Berkeley National Laboratory (LBNL) with expertise in energy and transportation systems engineering. For eight years he has been working in the spaces of sustainable transportation, renewable energy resources development, and energy efficiency. Mr. Sheppard’s current role at LBNL under the DOE SMART Mobility Initiative (Department of Energy System and Modelling for Accelerated Research in Transportation) is co-leading the development of the BEAM Framework (Behavior, Energy, Autonomy, and Mobility), an integrated systems approach to sustainable transportation analysis. BEAM involves agent-based simulation modeling of a fully multi-modal transportation system that includes public transit and shared/autonomous mobility services in addition to traditional modes.

Mogeng Yin, PhD Candidate, UC Berkeley Transportation Engineering

Mogeng Lin

Mogeng Yin is currently a PhD candidate in Transportation Engineering from UC Berkeley. He received a B.E. degree in Civil Engineering from Tsinghua University, Beijing, China, in 2013 and M.S. in Transportation Engineering from University of California, Berkeley, CA, USA, in 2014. His research interests include spatial data mining, urban computing, smart city, and machine learning.