Earth Data Analytics Courses at CU Boulder

These three courses comprise the professional certificate in Earth Data Analytics - Foundations. Throughout the certificate program, students work on capstone projects related to their topical interests and future career goals. Explore former student capstone projects here.

Earth Analytics Data Science Bootcamp (Geog 4463/5463)

Semester: Annually in the fall semester, online and in person
Instructor: Jenny Palomino
Open to: Professional certificate students, existing CU graduate and undergraduate students
Prerequisites: None
Credits: 3

Summary: This introductory, multidisciplinary course will provide core scientific programming skills required to efficiently work with a suite of earth systems data in Python. The course provides an introduction to the scientific programming, version control and collaboration skills required for efficient workflows. Students learn programming principles like functions and basic automation using loops and syntax. Students also use Git, GitHub, Bash, and Shell for version control and collaborative coding. The course will culminate with a project rather than a final exam. This course is technical. Students will code every day and finish the course with proficiency in using Python and Jupyter notebooks. No programming experience is required to take this course.

Specifically, in this course students will learn to:

  • Write clear, expressive and efficient modular code in Python to process and visualize different data types including spatial, time series and other formats.
  • Use programming principles including functions and basic automation with loops and syntax.
  • Design and write a basic algorithm to process data.
  • Optimize code sharing and reuse through code documentation techniques.
  • Employ data management best practices to facilitate efficient workflows and collaboration.
  • Use Bash/Shell to navigate the computer directory, create directories and interface with Git/GitHub.
  • Use Git/GitHub and Bash/Shell for version control, reproducible workflows, scientific collaboration and project management.
  • Organize documents and directories using sound data management approaches.
  • Effectively communicate science and collaborate on interdisciplinary group projects.

Build computationally intensive skills

The skills and tools taught in the earth analytics program are determined by market demand both in science and industry. Earth Lab conducts surveys of both industry partners and the scientific community to determine what tools and skills are in demand to optimize student marketability.

Earth Analytics - Python (Geog 4563/5563)

Semester: Annually in the spring semester, online and in person
Instructor: Leah Wasser
Open to: Professional certificate students, existing CU graduate and undergraduate students
Prerequisite: Geog 4463/5463
Credits: 3

Summary: This multidisciplinary course is focused on teaching students to efficiently process, integrate, analyze and visualize Earth data. Students will learn to work with a suite of data types, structures and formats to address major questions in earth science. Data science and programming tools are taught in the context of earth science topics including uncertainty, vegetation change, disturbance and extreme events (e.g. fires and floods) and social media data for disaster response. This course is technical. Students will code every week and finish the course with proficiency in using Python and Jupyter notebooks to create data driven reports. Lessons, assignments and the syllabus can be found on the earthdatascience.org webpage.

Specifically, in this course students will learn to:

  • Use Python to open, process, map and work with spatial data.
  • Work with diverse data formats (e.g. raster, vector, tabular and JSON), structures (e.g. social media, crowdsourced and spatial) and types (e.g. remote sensing, sensor network and ground-truthed).
  • Find and access data efficiently using websites and Programmatic APIs.
  • Work with and derive metrics from remote sensing data.
  • Use Jupyter Notebooks to maintain efficient workflows and to create fluid data driven reports that link data to analysis and process.
  • Effectively communicate science and collaborate on interdisciplinary projects.
  • Document your workflow using clean, expressive coding and following open science principles.

Earth Analytics Applications (Geog 5663)

Semester: Annually during the summer session, online and in person
Instructor: Jenny Palomino
Open to: Professional certificate students
Prerequisites: Geog 5463 and Geog 5563
Credits: 3

Summary: Students in this course will apply skills learned in prerequisite classes through working collaboratively on a data-intensive group project that is based on a real world issue. This project can be (1) provided to the student by one of Earth Lab’s industry or agency partners or (2) provided by the student from their current job, graduate thesis or dissertation. The project might include more advanced statistics or application development. It will ideally relate to a job that the student would like to have in the future. The final product will be a data-driven report and presentation.

Specifically, in this course students will learn to:

  • Apply skills acquired in prerequisite courses to find, organize, manage, process and extract insights from Earth datasets.
  • Apply skills acquired in prerequisite courses to maintain efficient workflows, especially through the use of collaborative tools like Git/GitHub.
  • Understand and address data uncertainty.
  • Effectively communicate science and collaborate on interdisciplinary group projects. 

Courses Not Currently Offered

Earth Analytics - R (Geog 4563/5563)

GEOG 4563/5563 was previously taught in the R programming language. It is currently not being taught in R but you can review the entire course online.

Semester: The R version of this course is no longer offered. However, the entire course is available online.
Instructor: Leah Wasser
Open to: Professional certificate students, existing CU graduate and undergraduate students
Prerequisites: None
Credits: 3

Summary: This course is focused on teaching students to efficiently process, integrate, analyze and visualize heterogeneous spatio-temporal data. Students will learn to work with a suite of data types, structures and formats. Students will finish the course with proficiency in the R programming language and R markdown to create data driven reports. Lessons, assignments and the syllabus can be found on the earthdatascience.org webpage.

In this course you will learn to:

  • Use R to open, process, map and work with spatial data.
  • Work with diverse data formats (e.g. raster, vector, tabular and JSON), structures (e.g. social media, crowdsourced and spatial) and types (e.g. remote sensing, sensor network and ground-truthed).
  • Find and access data efficiently using websites and Programmatic APIs.
  • Work with and derive metrics from remote sensing data.
  • Use R markdown to maintain efficient workflows and to create fluid data driven reports that link data to analysis and process.
  • Effectively communicate science and collaborate on interdisciplinary projects.
  • Document your workflow using clean, expressive coding and following open science principles.