This course introduces students to the theory, principles and applications of mathematical and computer modeling of spatial-temporal data as applied to cities. It will be based on two unified themes: an introduction to data science with an orientation toward decision-making and predictive analytics followed by frameworks for spatial-temporal data analysis. The 1st half of the course will cover predictive modeling using a wide array of examples, including predictive modeling, an advanced treatment of regression, visualization and graphics, and automated analysis for high dimensional data. Bayesian analysis, data ethics, privacy, and provides an introduction to analytics applications in citizen science, crowd-sourcing, and participatory sensing are introduced in the context of urban issues. The second half will introduce the principles underlying the conception, representation, measurement and analysis of spatial-temporal phenomena. The course will introduce frameworks for spatial-temporal data collection and analysis, including model and design-based estimation procedures as well as sampling and scaling strategies. Geographic information system (GIS) and other mapping techniques are introduced as methods for spatial data analysis and visualization.