Talk (non-conference) (Plenary/Keynote)

FZJ-2024-05761

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Deep learning can beat numerical weather prediction - what comes next?

Schultz, M. (Corresponding author)FZJ*

2024

Abstract: The past two years have witnessed an enormous evolution of machine learning models for weather prediction. What has been almost unthinkable a few years ago is now routinely confirmed: large-scale deep learning models trained on many years of reanalysis data can make more accurate predictions with longer lead times than classical numerical models. Recent developments also show the potential to use these models for ensemble forecasting and data assimilation. I will summarize the current state-of-the-art and point out where ongoing developments are heading and where I see the limitations of AI models for weather and climate.

---

Contributing Institute(s):

1. Jülich Supercomputing Center (JSC)

Research Program(s):

1. 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) (POF4-511)
2. Earth System Data Exploration (ESDE) (ESDE)

Appears in the scientific report 2024

---