Geospatial Data Science Applications: GEOG 4/590

Lecture 1: Introduction

Johnny Ryan
[email protected]
Office hours: Monday 15:00-17:00
 Welcome
Dr. Johnny Ryan, Assistant Professor of Geography

● BSc in Geography at University of Nottingham, UK

● MPhil in Polar Studies at University of Cambridge, UK
● PhD in Geography at Aberystwyth University, UK

● Researching glaciology, hydrology, remote sensing

Email: [email protected]
Office hours: Monday 15:00-17:00
 COVID Policies
● All classes will be held in-person in accordance with the latest university policies

● Mask wearing is mandatory indoors for all students

● Please do not come to class or lab if you are feeling sick or have been exposed

● Let me and/or Insang know if this happens and we will work with you to make up
the missed materials.
 COVID Policies
Time to get to know your neighbors!

● Please introduce yourself with:

○ your name
○ your year
○ where you’re from
○ your favorite place to eat in Eugene
 Overview
● What is Geospatial Data Science?
○ Spatial data (e.g. geometries and projections)
○ Coding (e.g. Python)
○ Collaborating (e.g. GitHub, Slack)

● Course schedule
○ Lectures, labs, grading

● Final project

● Some tasks
○ Complete background survey on Canvas
○ Join Slack workspace
○ Getting started in Wed/Fri lab session
 Geospatial data
● Vector data

● Network data

● Raster data
 Python
● Popular high-level programming language

● Easy-to-read

● Extensive library

● Free and open-source

○ Accessible
○ Can be examined, modified, and
improved

● Constantly evolving
 Git and GitHub
● Git
○ Version control software for tracking changes to a set of files

● GitHub
○ A cloud-based Git repository hosting service
○ Makes it easier to coordinate work among programmers
collaboratively developing source code during software
development

● Python and projects that use Python (e.g. matplotlib) are all maintained
and developed by a community of scientists and programmers on
GitHub

● An active, up-to-date GitHub profile, with contributions to open-source

project is a great way to provide evidence of skills
 Slack
● Messaging app that facilitates collaboration by
having all features in one place

● Starting to replace email, more secure, organized

● You should have received invitation to join course

workspace
○ Use the standalone desktop app rather than
the web interface

● We will use Slack for announcements, discussion,

and questions
○ Asking questions on Slack is not cheating!
 Course schedule
● Lectures: Monday 2pm in 106 Condon Hall
○ 8 lectures
○ Holiday on Jan 17, class presentations in Week 10

● Labs: Wednesday @ 2pm or Friday 10am in 442 MCK 207 Condon Hall
○ 7 labs
○ 2 labs to concentrate on final project
○ Class presentations in Week 10
 Course evaluation
● Lab assignments (45%) due every Friday 11:59 pm

● Final project (45%)

○ Presentation due March 6, 11:59 pm
○ Write-ups due March 11, 11:59pm

● Participation (10%)
○ Credit can be earned through attendance in lectures, participation in class
discussion (both virtual and in-person), visiting Professor and GE during
office hours, and helping other students in labs.
Working with
geospatial data
Working with
geospatial data

Machine learning
Working with
geospatial data

Machine learning

Key skills
Working with
geospatial data

Machine learning

Key skills

What we should
and shouldn’t do
 Final project
● 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

● Sharing of project ideas on Slack is encouraged so we can form teams

 Final project schedule
● Week 5: Discuss project ideas with peers and instructors, submit a short summary of
a project idea on the #final-projects Slack channel

● 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
 Final project schedule
● Week 5: Discuss project ideas with peers and instructors, submit a short summary of
a project idea on the #final-projects Slack channel

● 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
 Final project schedule
● Week 5: Discuss project ideas with peers and instructors, submit a short summary of
a project idea on the #final-projects Slack channel

● 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
 Final project schedule
● Week 5: Discuss project ideas with peers and instructors, submit a short summary of
a project idea on the #final-projects Slack channel

● 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
 Final project schedule
● Week 5: Discuss project ideas with peers and instructors, submit a short summary of
a project idea on the #final-projects Slack channel

● 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

I will send reminders out about upcoming milestones

 Some course themes
● Everything is open-source
○ All software we use is freely available
○ Labs can be completed anytime, anywhere from any OS
○ Course materials are publicly-available on the internet
 Some course themes
● Promote collaboration and communication
○ With instructors and peers
○ On GitHub and Slack
 Some course themes
● Learn about environmental challenges in the Western US
○ Urban planning and zoning
○ Hazards (e.g. wildfires, flooding)
○ Energy, climate, hydrology
 Some course themes
● Don’t try and write perfect code, if it works, it works

● Adapt code, don’t write code

● Make use of stackoverflow

● Ask peers

● Be scrappy
 Some course themes
● Take responsibility for learning

● Organize your files

● Check Canvas and Slack regularly

● Maintain your GitHub profile and repository

Some course themes
 By the end of this course you will…
● Have confidence using Python specifically for GIS and other geospatial data science
applications
○ In doing so, you will also be comfortable using Python for other things as well

● Be able to download, process, analyze, and visualize the main types of geospatial
data

● Automate boring GIS tasks (no more clicking!)

 By the end of this course you will…
● Learn how to solve real-world problems using spatial analysis

● Understand basic machine learning concepts for data science

● Collaborate on software development using version control

● Communicate results of data science project orally and as short write-up

 Getting started on this week’s lab
● Go to course page on GitHub:
○ https://github.com/JohnnyRyan1/geospatial-data-science
○ See Slack (or Canvas assignment) for links

● Operating systems… Linux, OSX are great, Windows is OK could

consider using Windows Subsystem for Linux