BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Learning for Medium-Range Global Weather Prediction - Prof. R
 ichard Turner and Stratis Markou\, University of Cambridge
DTSTART:20231101T110000Z
DTEND:20231101T123000Z
UID:TALK207913@talks.cam.ac.uk
CONTACT:Isaac Reid
DESCRIPTION:Over the last 18 months a quiet AI revolution has begun in the
  field of numerical weather prediction. Medium-term weather prediction inv
 olves forecasting several days to a couple of weeks in the future. The sta
 ndard approach to this problem is to run detailed global simulations of th
 e earth's atmosphere using a supercomputer -- so-called numerical weather 
 prediction (NWP). As little as one year ago\, researchers in this field ha
 d thought it unlikely that machine learning approaches would be competitiv
 e with numerical weather prediction any time soon. Since then a series of 
 papers have been released that apply advances in transformers and graph ne
 ural networks to this task. They have shown that deep learning weather pre
 diction models achieve a performance which is already competitive with sta
 ndard NWP\, but with a post-training computational cost that is 1000s of t
 imes cheaper. The deep learning based forecasts have also been shown to be
  surprisingly robust\, performing reasonably in the tails of distributions
  and accurately forecasting aspects of extreme events. Consequently\, weat
 her prediction centres like the European Centre for Medium-Range Weather F
 orecasts (ECMWF) are now building machine learning teams and publicly test
 ing deep learning forecasts (https://charts.ecmwf.int/products/pangu_mediu
 m-t-z?). This journal club will introduce the topic of deep learning based
  medium-term weather prediction\, it will walk through the two most influe
 ntial models -- Pangu and GraphCast -- comparing and contrasting them\, an
 d it will highlight opportunities for future work .\n\nSuggested reading: 
     \n1) Accurate medium-range global weather forecasting with 3D neural n
 etworks (https://www.nature.com/articles/s41586-023-06185-3)\;    \n2) The
  basics of transformers will be assumed - see here for an introduction: An
  Introduction to Transformers (https://arxiv.org/abs/2304.10557)\;    \n3)
  Additional suggested reading: GraphCast: Learning skillful medium-range g
 lobal weather forecasting  (https://arxiv.org/abs/2212.12794)
LOCATION:Cambridge University Engineering Department\, CBL Seminar room BE
 4-38.
END:VEVENT
END:VCALENDAR