Artificial Intelligence in the Built Environment (Fall 2023)

Undergraduate and Graduate course, University of Florida, Department of urban and regional planning, 2023

Introduction. The planning, design, and construction of the built environment is on the verge of a fundamental transformation. A key element of this transformation is a radical shift in paradigm from planning and design representations of unconnected data to practices with an overwhelming amount of information-rich data. Artificial Intelligence (AI), in particular Machine Learning (ML), provides planners, designers, and constructors with new models and methods to engage in these data-heavy processes in order to synthesize meaningful information for all areas of their practice from planning to design to fabrication to erection. This course provides the College of Design, Construction and Planning (DCP) students an opportunity to learn about application of AI in their disciplines.

Introduction to Urban Analytics (Spring 2023)

Graduate course, University of Florida, Department of Urban and Regional Planning, 2023

Introduction. This course introduces the primary modeling paradigms to analyze cities with an emphasis on analytical perspectives and urban applications. The course consists of four study modules with the first three introducing regression, network science, and machine learning and the module four discussing their integration. The regression module introduces linear and logistic regression from the statistics tradition, applied to the analysis of urban economy and mobility. The network module introduces the spatial networks, spatial regression, power-law scaling, and urban network dynamics. The machine learning module introduces supervised and unsupervised learning, and deep learning with applications to mobility networks and urban imagery. The course discusses the similarities and differences of the three analytical paradigms and introduces how to integrate them in the fourth study module. The course will also provide broad urban analytical perspectives by touching upon optimization, causal inference, generative models, and social justice in cities. Students will learn Python packages, such as Pandas, GeoPandas, and Scikit-learn to analyze urban mobility, economic development, resilience, and housing. This course focuses on intuition and application of the analytical tools to urban topics, rather than theory or math foundations. It provides future urban planners, designers, and engineers the critical analytical capacity to understand cities and address upcoming urban challenges.

Deep Learning for Urban Mobility

Graduate course, Massachusetts Institute of Technology, Department of urban studies and planning, 2019

Introduction. The course explores deep learning (DL) methods for urban mobility applications. Covers concepts of algorithmic prediction, interpretability, causality, and fairness in the context of urban mobility system design and policy making. Topics include demand prediction at both individual and aggregate levels, decision making with and without uncertainty, vehicle and ride sharing, built environment and travel behavior, traffic prediction and control, maps and information provision, and multimodal system design. Students learn intuitions and methods in DNN, CNN, RNN and reinforcement learning, build hands-on models using real-world datasets, and design and implement group projects. At the intersection of machine learning methods and urban mobility applications, the course seeks to reconcile the tension between generic-purpose models and domain-specific knowledge. Furthermore, the course envisions and critically reflects on how machine learning methods shape transportation research and mobility industry, and examines the potentials and pitfalls of their applications in urban mobility business and policies.