BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:AI weather forecasting: past\, present and future - Richard Turner
 \, University of Cambridge
DTSTART:20260227T160000Z
DTEND:20260227T170000Z
UID:TALK243397@talks.cam.ac.uk
CONTACT:Duncan Hewitt
DESCRIPTION:Weather forecasting is critical for a range of human activitie
 s including transportation\, agriculture\, industry\, as well as the safet
 y of the general public. Over the last two years\, machine learning models
  have shown that they have\nthe potential to transform the complex weather
  prediction pipeline\, but current approaches still rely on numerical weat
 her prediction (NWP) systems\, limiting forecast speed and accuracy. In th
 is talk\, some of the background on these\ndevelopments will be given. A n
 ew generation of machine learning model will then be introduced which can 
 replace the entire operational NWP pipeline. Aardvark Weather\, an end-to-
 end data-driven weather prediction system\, ingests raw observations and o
 utputs global gridded forecasts and local\nstation forecasts. Further\, it
  can be optimised end-to-end to maximise performance over quantities of in
 terest. It will be shown that the system outperforms an operational NWP ba
 seline for multiple variables and lead times for gridded and station forec
 asts. Finally\, the talk will end by discussing how these ideas might deve
 lop over the next few years\, including their application to multiple part
 s of the Earth system on multiple time-scales\, and their potential impact
  on climate modelling
LOCATION:MR2
END:VEVENT
END:VCALENDAR