Module 1: Introduction & Python Basics
What this module covers
This module provides an overview of the course and gets you started with the tools you’ll use throughout: Python, NumPy, Matplotlib, and Jupyter notebooks. No prior programming experience is required.
You’ll learn how to:
- Work with Jupyter notebooks (the format used for all lectures and practice exercises in this course)
- Use Python variables, lists, loops, and functions
- Work with NumPy arrays for numerical computation
- Create plots with Matplotlib
- Write reusable functions
Materials
Slides: Introduction to AI/ML (pdf)
Practice: Python Basics — A hands-on notebook covering core Python, NumPy, and plotting skills you’ll use in every subsequent module.
Context
In this course, you will learn the basic principles and practice of a wide range of powerful Machine Learning (ML) tools that have wide applicability in the Earth Sciences and beyond. The goal is for you to develop useful skills to apply in your current and future research and career, whether in academia or industry.
We use Jupyter Notebooks, which offer an interactive interface where you can mix code and text, organize your work into sections, and directly incorporate figures. All lecture notes are provided as interactive notebooks — not just static slides — so you can run every example yourself, modify parameters, and see what happens.
The course starts with the simplest ML tools (linear regression) and builds up to the most powerful deep learning methods (convolutional neural networks for satellite image analysis). Along the way, lectures aim to provide a deep understanding of how these methods work, while practice exercises let you apply these tools to real Earth Science problems.
Next module: Module 2: Univariate Linear Regression — your first ML algorithm.