Computational Tools in Climate Science: Part 9 - AI and Climate Change
NFDI4Earth
About This Course
Welcome to the "AI and Climate Change" course. This is the ninth part of the "Computational Tools for Climate Science" course series! Today's materials will provide an overview of data science and machine learning and how these topics can be applied to topics related to climate science and climate change. Particularly, you will explore a Earth System Model based data set that contains temperature, precipitation, and anthropogenic emission variables over a time span of half a century. Furthermore, you will learn how to set up machine learning models that can predict output values and categorize data..
Level
Intro, Beginner, Intermediate
Requirements
Prerequisites include some introductory programming skills in Python, as well as core math and science concepts. We expect participants to be familiar with fundamental Python and data storage concepts (variables, lists, dictionaries, data formats) as well as some key Python libraries like NumPy, matplotlib, cartopy, datetime, pandas, and Xarray.
Subject Area
Geosciences
Learning Objectives
- See how machine learning and AI can be used to address many different problems associated with climate change.
- Understand the basic principles of machine learning.
- Apply a basic machine learning technique to the problem of rising temperatures.
- Identify the pros and cons of applying machine learning methods in this domain.
What You Will Learn
- Introduction to Climate Change Impacts on the SDGs and the Role of AI
- ClimateBench Dataset and How Machine Learning Can Help
- Building and Training Random Forest Models
- Testing Model Generalization
- Testing Spatial Generalization
- Testing generalization to new scenarios
- Exploring other applications
Resources
Computational Climate Science syllabus by Climatematch
Computational Computational Tools in Climate Science by Climatematch
Computational Tools for Climate Science Course by neuromatch