This four-day course focuses on machine learning for numerical weather prediction (NWP). This will include:
- an overview on the use of machine learning in Earth Sciences,
- the introduction into the most important machine learning methods that are relevant for Earth Sciences,
- the introduction into software and hardware frameworks at ECMWF to facilitate the use of machine learning,
- and examples for the use of specific machine learning tools across the weather and climate prediction workflow and how they can be prepared for use in operational predictions.
As there are many general courses on machine learning available – including free online courses – this course will have a particular focus on the use of machine learning in the domain of Earth Sciences.
As well as lectures there will be discussion and hands-on sessions.
Main topics
- An overview on the use of machine learning in Earth Sciences
- Software for machine learning in NWP
- Hardware for machine learning in NWP
- Datasets that are available and data retrieval
- Regression and decision trees
- Deep learning
- Hybrid modelling
- High-performance computing readiness of machine learning
- Examples of machine learning applications
Requirements
Participants should have a good meteorological or a good machine learning background, or both. Participants should also have some limited experience with Python code and Jupyter notebooks. Basic experience with machine learning applications in Earth system sciences and the handling of Earth system data would be advantageous. Some practical experience in numerical weather prediction is an advantage.
All lectures will be given in English.