Machine Learning Applications in the Earth Systems Sciences

In this Jupyter Notebook, you are tasked with planning, implementing, and evaluating a machine learning solution for a real-world scenario. Given pre-configured code blocks and prepared data, you will create a problem statement, explore the data, experiment with model development, and ultimately make a recommendation on the utility of machine learning for your scenario.

Preview (Read Only)Get NotebookLearner HandbookRubric

Details

Learning Series

Machine Learning in the Earth Systems Sciences

Intended Audience

  • Earth Systems scientists
  • New and aspiring machine learning users
  • Graduate and upper-level undergraduate students

Learning Objectives

  1. Describe the data used in the scenario, including discussion of the context to the physical world
  2. Create and make strategic refinements to a machine learning model following a guided low-code workflow
  3. Describe a multifaceted classification model evaluation, including accuracy, precision, and recall scores
  4. Justify a decision on utility of a machine learning model based on evaluation metrics, physical context, impacts on the Earth Systems Science scenario

Suggested Prerequisite Skills

Author

NSF Unidata

In partnership with Metropolitan State University of Denver

This work was supported by NSF Unidata under award #2319979 from the US National Science Foundation.

Format

Jupyter Notebook

Duration

1 hour

Technical Requirements

For classroom support, you may request a JupyterHub from NSF Unidata. 

Last Update

March 2025

Contact

support-eLearning@unidata.ucar.edu