Skip to main content

Machine Learning for Earth Systems Modelling

Applications and New Directions

Online training course 3
Cutting edge applications of ML in weather and climate science


 October 2026
Online, self-paced


Fundamentals

Certification available

16

Single module

Topics

  • Computing services and tools
  • Machine learning

Overview

Coming soon – Autumn 2026

This third course in the Destination Earth Machine Learning for Earth Systems Modellingtraining series focuses on advanced applications of machine learning (ML) in weather, climate, and Earth-system science. Building on Courses 1 and 2, this advanced online course explores how machine learning is being applied across the full Earth-system modelling workflow, from operational forecasting, coupled atmosphere–ocean–land systems, downscaling, and data assimilation to hybrid AI–physics approaches, end-to-end modelling, and emerging foundation-model paradigms.

This free online course combines expert lectures, practical examples, applied notebooks, and community discussions using real-world Earth-system modelling examples relevant to Destination Earth (DestinE). Learners will explore current research directions, practical implementation challenges, operational readiness, and the evolving role of AI in Earth-system prediction.

Course information and registration

Course Start: Autumn 2026
Duration: 6-8 weeks
Estimated study load: 16 hours
Format: Online course, primarily asynchronous
Participation: free and open to anyone interested

If you are interested in taking the course, you can already register your interest by logging in and enrolling at the bottom of this page.

Target audience and prerequisites

This course is intended for advanced technical learners with a background in weather, climate, or Earth system sciences. The course is particularly relevant for:

• Researchers and developers in weather, climate, and Earth-system science
• Operational Numerical Weather Prediction (NWP) and climate-model developers
• Machine learning researchers working on environmental or geophysical data
• Advanced PhD students and postdoctoral researchers

Participants are expected to have the following prerequisite knowledge:

• Experience with Python and scientific computing tools (such as NumPy, xarray, PyTorch or JAX)
• Familiarity with machine-learning workflows and model evaluation 
• Forecast verification and uncertainty
• Basics of Numerical Weather Prediction (NWP) and Earth-system modelling,
• Understanding of core Machine Learning methods from Courses 1 and 2, including use and implementation of different neural network architectures

Prior completion of the following courses is strongly recommended, but not required:

Course Content

Tags

  • DestinE

Start this course

Self enrolment (Student)
Self enrolment (Student)
Back