Introduction to Machine Learning for Climate Scientists

Europe/Berlin
Room 034 (DKRZ Main Building)

Room 034

DKRZ Main Building

DKRZ Main Building, Bundesstraße 45a, 20146 Hamburg
Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)
Description

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.

Organized by

Caroline Arnold, Johannes Meuer, Étienne Plesiat

Contact
  • Wednesday, March 29
    • 1:00 PM 5:00 PM
      Day 1
      Conveners: Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)
      • 1:00 PM
        Introduction to Machine Learning 1h 25m
        • Get to know the typical workflow of a Machine Learning project
        • Recap the necessary Python concepts to write Machine Learning code
        Speaker: Caroline Arnold
      • 2:25 PM
        Examples for ML in Climate Science 20m
        Speaker: Christopher Kadow
      • 2:45 PM
        Coffee Break 30m
      • 3:15 PM
        Introduction to Pytorch 1h 45m
        • Recap on Neural Networks and Convolutional Neural Networks (CNNs)
        • Setup the tutorials on the JupyterHub
        • Introduction to PyTorch with examples
        Speaker: Etienne Plésiat
  • Thursday, March 30
    • 9:00 AM 1:00 PM
      Day 2
      Conveners: Caroline Arnold, Etienne Plésiat, Johannes Meuer (DKRZ)
      • 9:00 AM
        PyTorch applied to Climate Science 1h 45m

        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 AM
        Coffee Break 30m
      • 11:15 AM
        Introduction to using Pytorch on Levante 1h 45m
        • Introduction to SLURM for job scheduling on Levante
        • Description of Advanced Use-Case
        • Training a computational expensive model on Levante
        Speaker: Johannes Meuer (DKRZ)