Spatial Statistics and Data Analytics
The goal of this course is to familiarize students with a number of statistical and data mining techniques commonly used for analyzing different types of urban data. The course will have two key parts: 1) regression analysis for urban data, and 2) identifying patterns in urban data. Even though the course will cover the theory and mathematics behind the majority of the statistical methods, it will focus mostly on their applications. Students will learn when each statistical test should be used and the assumptions behind each test. In addition, while the R software will be used for most of the course, students will also learn to use several other software packages, such as GeoDa and VIS-STAMP. Finally, students will learn how to describe and interpret the output of the analyses that they run.
Public Policy Analytics
Data scientists convert data into actionable intelligence. While most private sector data scientists optimize for profit, their public sector counterparts must address multiple complex bottom lines including economics, equity, politics, bureaucracy and social cohesion. This course teaches students how to wrangle government data; how to mine it for descriptive and predictive intelligence and how to communicate results to non-technical decision-makers. Broadly, coursework is focused on spatial analysis and geospatial machine learning and taught 70/30 in R and ArcGIS. Use cases include home price prediction, forecasting in criminal justice, land use modeling, transportation modeling and real estate site suitability. Prerequisites include vector and raster GIS and introductory statistics.
Geospatial Cloud Computing & Visualization
Modeling Geographic Space
The major objective of this course is to explore the nature and use of raster-oriented geographic information systems (GIS) for the analysis and synthesis of spatial patterns and processes. Modeling Geographical Space course is oriented more toward the qualities of geographical space itself (e.g. proximity, density, or interspersion) than the discrete objects that may occupy such space (e.g. water bodies, land parcels, or structures).
Land Use and Environmental Modeling
Urban and environmental planners are using spatial data and increasingly sophisticated empirical models to analyze existing patterns, parameterize key trends and processes, forecast alternative futures, and visualize key results for non-technical decision-makers. This course focuses explicitly on these themes. By the end of the course, students will understand how to parameterize spatial data specifically for modeling as well as how to take top down and bottom up approaches to modeling comparable phenomenon. This is a GIS-oriented class that will rely on statistical modeling. We will use a variety of software packages including ArcGIS, R, the HEC Suite of hydrological tools and NetLogo.
Geospatial Data Science in Python
This course will provide students with the knowledge and tools to turn data into meaningful insights, with a focus on real-world case studies in the urban planning and public policy realm. Focusing on the latest Python software tools, the course will outline the "pipeline" approach to data science. It will teach students the tools to gather, visualize, and analyze datasets, providing the skills to effectively explore large datasets and transform results into understandable and compelling narratives. The course is organized into five main sections: Exploratory Data Science; Introduction to Geospatial Data Science; Data Ingestion & Big Data; Geospatial Machine Learning; Data Visualization & Storytelling.
Satellite remote sensing is the science of converting raw aerial imagery in to actionable intelligence about the built and natural environment. This course will provide students the foundation necessary for application of machine learning algorithms on satellite imagery. Use cases include building footprint detection, multi-class object detection in cities and land cover/land use classification. The students will learn basic concepts of machine learning, including unsupervised and supervised learning, model selection, feature elimination, cross-validation and performance evaluation. After learning traditional methods and algorithms, the course will focus on recent deep learning methods using convolutional neural networks and their application on semantic image segmentation. Prerequisites include 'Geospatial Data Science in Python' or equivalent.
This course offers students an opportunity to work closely with faculty, staff, local practitioners, and each other on independent projects that involve the development and/or application of geographic information system (GIS) technology.
Musa/Smart Cities Practicum
This course pairs students with cities to work on real world data science projects. Students will develop the entire pipeline over the course of the semester. This includes the collection of unstructured data, development of spatial and statistical analytics and the visualization of these analytics by way of data dashboards.