Geography

Integration of Geography and AI, or GeoAI (a subfield of spatial data science), provides novel approaches for addressing a variety of geospatial problems in the natural environment and our human society. Hands-on computing labs using real-world geospatial data to address such AI topics as: image classification, object detection, scene segmentation, simulation and interpolation, retrieval and question answering, on-the-fly data integration, and geo-enrichment.

An introduction to geodata analysis using R. The course will be taught from the perspective of geographical and climate data analysis but serves as a broad introduction to the high-level programming language, R, as well as applied spatial data analysis. Students will load and manipulate data of different types, perform a variety of statistical analyses, generate graphical output, and create productive workflows using R alone. The primary outcome will be to facilitate students’ use of R to analyze data of their own choosing on a final project. Students will present these methods to the class for others to critique, analyze and learn from. Code sharing and re-use is highly emphasized, as is collaboration. The course is designed as a 1-hour lecture plus 2-hour lab each week.

It is often the case that real-world systems can be represented as networks of many interacting components. Examples include information (the World Wide Web, citation), social (friendship, classmates), physical (transportation, distribution), biological (food chain, brain) systems, and so forth. Many of these networks are essentially spatial, meaning each node can be associated with a location somewhere in the real world. Based on recent advances in network science and GIScience, this course teaches the fundamental concepts, models, and techniques for describing, visualizing, measuring, and analyzing networks. It also introduces their applications in geography, transportation, social science, etc. A series of labs using the popular network analysis package Gephi and GIS software ArcGIS are also designed to help students gain hands-on experience in visualizing and analyzing networks.

Focuses on how the Earth’s surface is visualized, explored, and analyzed in digital formats (e.g. maps, satellite images, aerial photos). Provides an introduction to fundamental concepts of digital geographic data to understand the Earth environment and human society based on the vast quantities of geographic information in our ever-changing world.

Data drives today’s world and over 80% of that data is geographic. Increasing volume and varying formats of these geospatial big datasets have posed new challenges. Introduces relevant concepts (e.g., 5 V’s) and techniques (e.g., cloud computing) of big (spatial) data as well as its applications in the real world. Hands-on experiences with Volunteered Geographic Information (VGI), analyzing geotagged tweets, and visualizing spatial datasets.

Geographic Information Systems (GIS) as the technology for creation, modification, display and analysis of spatial information. Develops knowledge of GIS, competence in geographic databases and familiarity with computer software and hardware.

Focuses on the design of GIS-based models to address health and healthcare issues. Topics include a conceptual framework, landscape epidemiology models, disease diffusion models, health accessibility, human health behavior and location-allocation of health services. Laboratory section provides hands-on experience applying these models with GIS tools.

Introduces the theory and application of digital imagery data in geographical research with a hands-on, lab-based approach.

Introduces basic programming concepts; instruction in popular programming languages for geospatial processing, applications, and modeling in ArcGIS environment.

Many phenomena of interest in physical, social and cyber environments can be thought of as networks within geographic context. Teaches methods for analyzing these spatial networks, and introduces their applications in geography, transportation, hydrology, epidemiology, social science, etc.

Introduces fundamentals and practices of advanced geostatistical analysis (kriging), which addresses optimal spatial interpolation. Geostatistics are currently applied in diverse disciplines such as geography, geology, engineering, hydrology, urban studies and epidemiology.

Integration of Geography and AI, or GeoAI (a subfield of spatial data science), provides novel approaches for addressing a variety of geospatial problems in the natural environment and our human society. Hands-on computing labs using real-world geospatial data to address such AI topics as: image classification, object detection, scene segmentation, simulation and interpolation, retrieval and question answering, on-the-fly data integration, and geo-enrichment.

Introduction to geodata analysis using programming. Broad introduction to the programming language as well as applied spatial data analysis. Facilitates students’ use of programming to analyze data of their own choosing on a final project. Code sharing and re-use is highly emphasized, as is collaboration.

Geographic and cartographic techniques for geospatial analysis of risk, vulnerability, and resilience using ArcGIS. Learn to utilize physical and human geographic datasets for multiple hazard contexts including hydrometeorological, climatological, and geophysical hazards.

Focuses on GIS applications in spatial analysis and ecology to address common research issues related to zoonotic diseases which affect animals and humans.

Instruction on geographic and cartographic techniques for geospatial analysis of population, demographic, and socioeconomic data using ArcGIS Pro. Students identify and utilize current and historical secondary population data sources for GIS analysis of population changes, and for mapping of segregation, inequality, and well-being indicators.

Provides a fundamental understanding of the Python programming language with a core focus on ingesting, displaying, and analyzing observational meteorological data and numerical weather model data.

Overview of radar and satellite remote sensing as used in the atmospheric sciences, including the principles of atmospheric radiative transfer, the retrieval of atmospheric variables, and emphasis on geospatial interpretation of imagery for different weather systems.

Meteorological and climatological concepts related to hurricanes. Forecasting current activity, researching past storms and analyzing storm structure, damage and future trends.

Atmospheric teleconnections are recurring large-scale patterns of pressure and circulation anomalies. They can influence temperature, rainfall, storm tracks and jet stream location and intensity. Examines how these patterns were discovered, how the index that characterizes the phase of each teleconnection is calculated and the weather associated with different phases.

How atmospheric data are collected and analyzed for meteorologic and climatologic-scale research. Where various types of data are obtained and how to analyze data to answer specific research questions.

Introduces regression models capable of dealing with spatial auto-correlation; develop statistical models and estimate with computer software.

Investigates techniques for evaluating the risks of extreme events related to water in our environment. Presents data and methodologies for estimating the rarity of phenomena including excessive rainfall totals, high and low river levels, coastal storm surge and waves, and drought.

Introduces the spatial epidemiology of vector-borne diseases (VBDs) and geospatial methods for monitoring, mapping and modeling them. Provides hands-on experiences for mapping and modeling risk of VBDs via GIS-based labs.