VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Machine Learning for Earth and Planetary Sciences II
Last Updated: 2026-07-21 00:35:29
Abstract
This class provides an introduction to machine learning concepts, techniques and algorithms and their applications in Earth and Planetary Sciences. The course will cover both the fundamentals and application of machine learning techniques for research. Emphasis will be placed on unsupervised and probabilistic methods and their use in Earth and Planetary Sciences.
Objective
Students will learn the fundamentals of machine learning, data handling, data visualization and data analysis using python. A variety of unsupervised and probabilistic learning techniques will be introduced and applied throughout this course. In completing the course, students will learn how to: - Generate hypotheses from data. - Make predictions from data. - Evaluate a model’s performance. - Apply machine learning techniques to their own research.
Content
Machine Learning for Earth and Planetary Sciences II begins on Week 5 of the spring semester and consists of 2 hours of interactive lectures per week. Exercises focused on data handling, implementation of machine learning methods and analysis are assigned each week and culminate with a course-wide data analysis competition. This course will cover a variety of machine learning topics used by Earth and Planetary scientists, including: - Unsupervised learning (e.g. k-means clustering, PCA and t-SNE) - Semi-supervised learning - Ensemble learning methods (e.g. Random Forest) - Hidden Markov Models - Bayesian Inference - Applications of machine learning and artificial intelligence in Earth and Planetary Sciences Machine Learning for Earth and Planetary Sciences I is not required for enrollment in this course. Pre-requisites include Mathematics I - IV or equivalent; Some experience with programming in either python, R, or MATLAB