Advanced Transportation Data Analysis: Introduction to Machine Learning (Online)

Instructor: Zeyu Wang, Ph.D. Researcher, and Don MacKenzie, Professor, Civil and Environmental Engineering University of Washington

When: Sept 24th - Sept 25th, 2 days - 8:30am - 1pm each day

Where: Synchronous (Live) Online

Cost: $200

Description:

This two-day workshop introduces transportation professionals, analysts, and planners to the core concepts and applied methods of machine learning (ML) in the context of transportation systems. Participants will learn how to work with transportation datasets to predict outcomes, classify patterns, and uncover structure in complex urban systems. The first day focuses on foundational predictive modeling, covering regression and classification techniques using hands-on coding exercises grounded in real-world mobility data. The second day explores neural networks, clustering methods, and ethical considerations around bias, overfitting, and deployment of AI in transportation operations and planning. Participants will explore how supervised and unsupervised learning can support use cases such as charging station placement, demand forecasting, and user segmentation. They will also reflect on the limitations of algorithmic tools and the importance of responsible AI implementation in the public sector.

Audience:

This course is designed for transportation practitioners, public agency staff, and data-savvy professionals with a basic understanding of data analysis who seek to acquire knowledge of machine learning tools and their applications in enhancing transportation planning and engineering practices. No prior experience with machine learning is required. Past participation in the PacTrans Workforce Development Institute's Introduction and Intermediate Data Analysis courses is helpful, but not required.

Learning Outcomes:

By the end of the workshop, participants will be able to:

• Differentiate between regression, classification, clustering, and deep learning techniques
• Apply supervised and unsupervised learning methods to transportation datasets
• Understand the strengths and limitations of various ML models in forecasting and segmentation
• Interpret model performance and assess generalization risks
• Recognize ethical challenges and risks of bias in transportation AI systems
• Identify appropriate use cases for ML tools in planning and operational contexts

Instructor Bios:

Zeyu Wang is a Ph.D. student and research assistant in Urban Design and Planning and Civil & Environmental Engineering at the University of Washington. His research focuses on the use of spatiotemporal data and visual intelligence techniques to analyze and improve urban environments, with an emphasis on urban imagery sources such as street-level and aerial imagery. With years of experience in spatial analytics and urban computing, Zeyu applies advanced machine learning and computer vision methods to understand patterns of human mobility, urban form, and spatial inequality. Dedicated to enhancing quality of life and promoting social equity, his work seeks to bridge technology and urban planning to support more inclusive and sustainable cities. Zeyu holds a master’s degree in Urban Analytics from the National University of Singapore (NUS), and has published in leading journals in urban science, geographic information systems, and computer science. He also serves as a peer reviewer for top journals in these fields, contributing to the advancement of interdisciplinary urban research.

Don MacKenzie, Allan & Inger Osberg Professor of Civil & Environmental Engineering, University of Washington. Don MacKenzie directs the UW’s Sustainable Transportation Lab, where his research combines data science and behavioral analysis to understand and improve transportation systems, with a focus on emerging technologies like electric vehicles and mobility services. His team applies statistical, machine learning, and causal inference methods to practical problems in transportation policy, modeling, and technology assessment. Dr. MacKenzie earned his PhD from MIT’s Engineering Systems Division, and teaches for the UW’s on-campus Transportation Engineering and online Master of Sustainable Transportation programs, including courses in introductory and intermediate applied statistics, research design, energy, climate change, sustainability, and transit planning.