LEAP Education

Climate Prediction Challenges with Machine Learning

Spring 2025 (Syllabus)

A project-based learning course where teams of climate science and data science students collaborate to create machine learning predictive models for challenges inspired by LEAP's research.

Material and links are being updated for 2025. Some links are for 2022; there will be some significant changes.

Shortcuts: Project 1 | Project 2 | Project 3

---

Project cycle 1: Jupyter Notebook for Exploratory Data Analysis

(starter codes)

Week 1 (Jan 20)

• Introduction to LEAP CPC (Zheng)
• Introduction to Earth Systems and Climate Change (McKinley)
• Project 1 description Hurricanes and Climate Change starts
  • A tutorial on LEAP Pangeo
• Team activities
  • Self introduction and a fun fact
  • The LEAP crossword challenge
  • Find a time to review and discuss project 1 materials as a group

Week 2 (Jan 27)

• Tutorial on EDAV (Zheng)
• A deep dive into Project 1
• Project 1 starter codes (Jiaxu Li)
• Discussion and Q&A

Week 3 (Feb 3)

• Presentation and submission instruction (Zheng)
• Team lightning shares
• Discussion and Q&A

Week 4 (Feb 10)

• Project 1 presentations

---

Shortcuts: Shortcuts: Project 1 | Project 3

Project cycle 2: Parameterizing Earth System Models with Machine Learning

Follwing the work of Sane, A., Reichl, B. G., Adcroft, A., & Zanna, L. (2023). Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer Using Neural Networks. Journal of Advances in Modeling Earth Systems, 15(10). doi:10.1029/2023ms003890

([starter codes])

Week 5 (Feb 17)

• [Project 2] starts.
• Introduction to Project 2 (McKinley)
• [Tutorial] [The challenge of parameterization] (McKinley)
• Project 2 [starter codes]
• Discussion and Q&A

Week 6 (Feb 24)

• [Tutorial] [Ocean mixing] (McKinley)
• Brainstorming, Discussion and Q&A

Week 7 (Mar 3)

• Visit by study lead author Dr. Sane
• Discussion and Q&A
• Group work

Week 8 (Mar 10)

• Group work

Week 9 (Mar 24)

• Project 2 presentations

---

Shortcuts: Project 1 | Project 2

Project cycle 3: Machine Learning with Sparse Data

(starter codes)

Week 10 (Mar 31)

• Project 3 starts.
• Climate Science Tutorial on "Air-Sea Flux of CO2" (McKinley)
• Review of starter codes
• Discussion and Q&A

Week 11 (Apr 7)

• Tutorial on decision tree, random forests and xgboost (Zheng)
• Discussion of papers and Q&A
• Discussion of research ideas

Week 12 (Apr 14)

• Group work

Week 13 (Apr 21)

• Tutorials on explainable AI (Zheng)
• Group work

Week 14 (Apr 28)

• Project 3 presentations

Shortcuts: Shortcuts: Project 1 | Project 3