Introduction to Statistical Learning for Atmospheric and Climate Sciences
28-29 August 2018
A two-day block course on “An introduction to Statistical Learning for Atmospheric and Climate Sciences” will be held at the Institute for Atmospheric and Climate Sciences, ETH Zurich on 28-29 August 2018. The course will provide an introduction to Statistical Learning methods for beginners and practitioners in the context of Atmospheric and Climate Science applications, featuring both overview lectures of applications and methods, and hands-on exercises.
Target group
The anticipated target group for the workshop consists of M.Sc/PhD students and PostDocs, who have a (practical) interest in Statistical Learning / Machine Learning / Data Science, but who had so far only little or no experience to Statistical Learning, and thus would like to gain an introductory overview. The course is open to everyone interested, exercises are limited to 30 participants (on a first-come-first-serve basis). No credit points can be given for the course.
Content & Lecturers
The course will consist of alternating overview lectures and hands-on practical exercises. Lectures will cover theoretical basics of Statistical Learning (Exploratory Analysis, Linear regression, sparse linear models, non-linear supervised learning) and a general overview and outro of applications of Statistical Learning in the Atmospheric and Climate Sciences. Exercises will allow the participants to understand, test and evaluate different methods in a “real-world” climate-science example (for details, see program attached). Exercises will be done in the R environment (https://www.r-project.org/), which is a specialized tool for statistical computing.
Materials
Slides & Exercises are available for download: https://iacweb.ethz.ch/staff/sippels/stat_learning_course (password will be provided during the course)
Venue
Lectures and exercises take place in the main building of ETH Zurich: Lectures: HG D 3.2; Exercises: HG E 19.
Costs & Registration
The course is free. Registration is required. Registration to exercises no longer possible. You can still register for lectures. – please regisister here
Program
Download Download full program (PDF, 117 KB)