Geospatial Big Data is an extension to the concept of Big Data with emphasis on the
geospatial component and under the context of geography or geosciences.
It is used to describe the phenomenon that large volumes of georeferenced data
(including structured, semi-structured, and unstructured data) about various aspects of
the Earth environment and society are captured by millions of environmental and human
sensors in a variety of formats such as remote sensing imageries, crowdsourced maps,
geotagged videos and photos, transportation smart card transactions, mobile phone data,
location-based social media content, and GPS trajectories.
This course will introduce the theory, techniques, and analytical methods for Big Data
Methods for storing, processing, analyzing, and visualizing various types of geospatial
big data using advanced Python programming will be introduced.
The course is designed for students who have programming experience or have finished
Geog378 (or CS220, or other programming introduction courses) previously and want to
reinforce the programming skills and learn AI and machine learning methods for solving
geospatial big data problems.
This course includes lectures and lab exercises.
The knowledge and skills learned in this course further prepare students for an emerging
career of (Geospatial) Data Science.
Course Learning Objectives:
Understand the fundamental concepts in geospatial big data
Understand the characteristics involved in developing computational models and
analytical methods for geospatial big data
Know the challenges in storing, managing, processing, analyzing, visualizing and
verifying the quality of data
Know the major high-performance platforms for big data processing
Be familiar with Python programming for (spatiotemporal) data analysis and machine
Work and collaborate in teams and get things done under time pressure
Demonstrate higher-order synthesis and spatial analysis skills in spatial data