Introduction to Deep Learning for Climate Scientists

19 Mar 2025, 13:00 → 21 Mar 2025, 12:30 Europe/Berlin

Room 034 (DKRZ Main Building)

Adeniyi Mosaku (DKRZ), Caroline Arnold (HEREON), Etienne Plésiat (DKRZ), Johannes Meuer (DKRZ), Paul Keil (HEREON)

Target group: beginner in Deep Learning with some Python experience

Deadline for registration: February 14 17:00 CET

Machine learning, and more particularly deep learning, is gaining popularity among climate scientists. While many tutorials and courses are available, researchers often face challenges in applying the concepts to climate data and adapting them to address the specific needs of their research.

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

The course will be held from March 19 13:00 to March 21 12:30 at DKRZ seminar room 034. Coffee breaks will be provided during the workshop.

Participants are required to have a working knowledge of Python.

Wednesday, 19 March

13:00 → 17:30 Day 1

Conveners: Adeniyi Mosaku (DKRZ), Paul Keil (HEREON)

13:00 Introduction to Machine Learning

• A comprehensive overview of the concepts and principle behind Machine Learning
• Exploration of real-world applications of Machine Learning
• Differentiating different Machine Learning types
• Introducing popular Machine Learning tools and frameworks

Speaker: Adeniyi Mosaku (DKRZ)

14:45 Coffee Break

15:00 Architectures and Applications

• An overview of state of the art Deep Learning Methods
• Examples from weather, climate and beyond
• Explainable AI

Speaker: Paul Keil (HEREON)

16:45 Coffee break

17:00 Accounts setup

• Preparation of the DKRZ accounts for the Pytorch tutorials

Speaker: Paul Keil (HEREON)

Thursday, 20 March

09:00 → 17:30 Day 2

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

09:00 Introduction to PyTorch: a simple Climate Science case study

• Definition of the task
• Creation of the training, validation and test datasets
• Building the CNN

Speaker: Etienne Plésiat (DKRZ)

10:45 Coffee Break

11:00 Introduction to PyTorch: a simple Climate Science case study

• Training the model
• Testing the model
• Improving the model

Speaker: Etienne Plésiat (DKRZ)

12:30 Lunch break

14:00 Introduction to Pytorch Lightning

• Learn the basics of the deep learning framework Pytorch Lightning
• Write deep learning code that is flexible and performant

Speaker: Caroline Arnold (HEREON)

14:45 Advanced Deep Learning use-case: Reconstructing missing climate data

• Design and implement inpainting CNN for reconstructing climate data

Speaker: Johannes Meuer (DKRZ)

15:45 Coffee break

16:00 Advanced Deep Learning use-case: Reconstructing missing climate data

• Train the model with different configurations
• Validate the model on test data

Speaker: Johannes Meuer (DKRZ)

Friday, 21 March

09:00 → 12:30 Day 3

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

09:00 Advanced Deep Learning Use Case: AI Weather Prediction

• Learn about AI weather models that can take it up with numerical weather prediction

Speakers: Caroline Arnold (HEREON), Paul Keil (HEREON)

09:45 Coffee break

10:00 AI Weather prediction in practice

• Run a global AI weather prediction with a pretrained deep learning model

Speakers: Caroline Arnold (HEREON), Paul Keil (HEREON)

10:00 Everything You Always Wanted to Know About Deep Learning* (*But Were Afraid to Ask)

• Open discussion about the workshop material and deep learning concepts
• Collaborative support on specific Climate Science projects

Speakers: Etienne Plésiat (DKRZ), Johannes Meuer (DKRZ)

12:00 Closing remarks

Speaker: Paul Keil (HEREON)