Course materials for Geospatial Data Science Applications (GEOG 4/590) taught at the Department of Geography, University of Oregon
Instructor: Johnny Ryan
TA: Insang Song
Lecture: Mondays at 14:00
Labs Wednesdays at 14:00 and Fridays at 10:00
This course introduces students to emerging geospatial data science methods for addressing important environmental challenges in the western USA. The course will be taught as a series of short lectures and longer computer labs in which students will learn how to use Python to process (e.g. resampling, manipulating, interpolating), analyze (e.g. machine learning), and visualize (e.g. plotting, mapping) geospatial data. Students will apply these newly developed skills to real world applications (e.g. water management, renewable energy, agriculture, hazards, and climate change). In doing so, students will become practitioners of geospatial data science who are familiar with a variety of data sources including those derived from satellite remote sensing, climate models, weather stations, census bureau, crowdsourced maps, and GPS. The course will be best suited for students who already have some programming (e.g. CIS 122) and GIS (e.g. 481) experience. The skills developed during this course will be directly applicable to a career in (geospatial) data science.
Learning outcomes:
- Improve Python skills
- Learn how think computationally and statistically
- Solve real-world problems using spatial analysis
- Understand basic machine learning concepts for data science
- Manage individual and group software development using version control
- Collaborate on a group project
- Communicate results of data science project orally and as a short write-up
The course will be taught over ten weeks, with a lecture on Monday and lab on Friday. The lectures will be interactive, often providing a recap of the previous lab. The labs will introduce key concepts of geospatial data analysis using code examples.
| Week | Date | Lecture x 1 hour | Lab x 2 hours | Project |
|---|---|---|---|---|
| 1 | Jan 3 | Introduction | Getting started with Python and GitHub | |
| 2 | Jan 10 | Vector data | Wildfire and Census data | |
| 3 | Jan 17 | No class (holiday) | Walking distances | |
| 4 | Jan 24 | Gridded data | Remote sensing and climate reanalysis | |
| 5 | Jan 31 | Machine learning | House price prediction | Submit project ideas |
| 6 | Feb 7 | Code management | Collaborating on GitHub | Initialize project |
| 7 | Feb 14 | Data access | Mountains and ski resorts | |
| 8 | Feb 21 | Visualization | Project work | Project check-in |
| 9 | Feb 28 | Discussion | Project work | |
| 10 | Mar 7 | Project presentations | Project presentations | Submit project write-up |
An essential component of this course is the final project which provides an opportunity to explore a particular topic of interest using some of the skills developed in this course. Students can work independently or in groups of two or three.
- Week 5: Discuss project ideas with peers and instructors, submit a short summary of a project idea on Slack.
- Week 6: Form teams, create GitHub repo, and provide some basic info about project as a
README.md. - Week 8: Provide informal update to instructors, ensure data has been accessed, goals are accomplishable.
- Week 10: Present project to class and submit write-up by the end of the week.
We will use Slack for most communication and discussion. Please join the course workspace with your UO email address. See Canvas announcement for invitation link. We recommend that you use the standalone desktop app rather than the web interface.
All the slides, assignments, and lecture notes are available under a CC BY-SA license. The terms of this license are:
This license allows reusers to distribute, remix, adapt, and build upon the material in any medium or format, so long as attribution is given to the creator. The license allows for commercial use. If you remix, adapt, or build upon the material, you must license the modified material under identical terms.
So please use and adapt these materials as you see fit but consider providing attribution to this repository. You can also show your support by starring this repository.
When putting together this course I relied heavily on David Shean's Geospatial Data Analysis course and Ryan Abernathey's Earth and Environmental Data Science course.