4–5 Sept 2023
University Club
Europe/Berlin timezone
This workshop was a great success. A second event of this series is in planning. See https://cesoc.net/workshop-on-large-scale-deep-learning-for-the-earth-system/

The last year has seen tremendous progress on large scale machine learning for numerical weather prediction. In the workshop we will take stock of the developments and discuss possible next steps and open research frontiers. For this, the workshop will bring together researchers from industry, modeling centers and academia and provide a forum for detailed discussions on the subject.

The workshop will be a mixture of talks and discussions to allow for a free exchange of ideas and help propel the field forward. Topics include:

  • Network architectures and training protocols for numerical weather prediction
  • Towards operational use of machine learning-based numerical weather prediction
  • Uncertainties and ensemble methods
  • Training on observational data
  • Sub-seasonal and seasonal forecasts and climate projections

 

For details about the scientific program, please see http://graphics.cs.uni-magdeburg.de/workshop/. 

A pdf copy of the program is available here

Abstract submission: closed

Starts
Ends
Europe/Berlin
University Club
Universitätsclub Bonn e.V. Konviktstr.9 53113 Bonn Germany
Go to map

The meeting will start on Monday, Sept 4th at 9:30 h and lasts until Tuesday, Sept 5th at 17:00 h. Please arrive at least half an hour before the start of the meeting to regioster and assume your seat.