Introduction to Machine Learning for Climate Scientists

29 Mar 2023, 13:00 → 30 Mar 2023, 13:00 Europe/Berlin

Room 034 (DKRZ Main Building)

Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)

Registration is closed to the exceptionally high demand

 

Target group: intermediate

Machine learning is becoming a popular method for climate scientists. While there are many tutorials and courses available, researchers often face challenges when applying the tutorial concepts to actual climate data, that can be quite different from standard machine learning datasets.

Therefore, we are offering the first Introduction to Machine Learning for Climate Scientists at DKRZ. The course will be held in person, and the number of participants is limited to 20.

Participants are required to have a working knowledge of Python.

The workshop is co-sponsored by Helmholtz AI.

Wednesday, 29 March

13:00 → 17:00 Day 1

Conveners: Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)

13:00 Introduction to Machine Learning

• Get to know the typical workflow of a Machine Learning project
• Recap the necessary Python concepts to write Machine Learning code

Speaker: Caroline Arnold

14:25 Examples for ML in Climate Science

Speaker: Christopher Kadow

14:45 Coffee Break

15:15 Introduction to Pytorch

• Recap on Neural Networks and Convolutional Neural Networks (CNNs)
• Setup the tutorials on the JupyterHub
• Introduction to PyTorch with examples

Speaker: Etienne Plésiat

Thursday, 30 March

09:00 → 13:00 Day 2

Conveners: Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)

09:00 PyTorch applied to Climate Science

Using a simple example, we will see how to:
- Load/split a climate dataset
- Build a CNN
- Train the model
- Test the model

Speaker: Etienne Plésiat

10:45 Coffee Break

11:15 Introduction to using Pytorch on Levante

• Introduction to SLURM for job scheduling on Levante
• Description of Advanced Use-Case
• Training a computational expensive model on Levante

Speaker: Johannes Meuer (DKRZ)