Welcome to Hands-on Machine Learning for Earth and Environmental Sciences

This book is the Fall 2025 edition.
Here you’ll find materials on scientific programming, machine learning, deep learning, and trustworthy AI for geoscience applications.

Introduction

• Running Python scripts

(Part I) Basics of Scientific Programming for Applied Machine Learning

• 1. Introduction to Python for Earth and Environmental Sciences

(Part II) Basics of Machine Learning for Earth and Environmental Sciences

• 2. Linear Regression for Regression, Logistic Regression for Classification and Statistical Forecasting
• 3. Decision Trees, Random Forests, Support Vector Machines and Environmental Risk Analysis
• 4. Unsupervised Learning (Clustering, Dimensionality Reduction) and Environmental Complexity

(Part III) Deep Learning for the Geosciences

• 5. Artificial Neural Networks and Surrogate Modeling
• 6. Convolutional Neural Networks and Remote Sensing
• 7. Recurrent Neural Networks and Hydrological Modeling
• 8. Graph Neural Networks and Interconnected Systems

(Part IV) Towards Trustworthy AI

• 9. Explainable Artifical Intelligence and Understanding Predictions
• 10. Generative Modeling and Uncertainty Quantification
• 11. Hybrid Modeling and Knowledge-Guided Learning