BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//juliacon-2022//speaker//A9SQSW
BEGIN:VEVENT
SUMMARY:SpeedyWeather.jl: A 16-bit weather model with machine learning - M
 ilan Klöwer
DTSTART:20220728T171000Z
DTEND:20220728T172000Z
DTSTAMP:20260811T180304Z
UID:pretalx-juliacon-2022-DZFPGX@pretalx.com
DESCRIPTION:We present SpeedyWeather.jl\, a global atmospheric model curre
 ntly developed as a prototype for a 16-bit climate model incorporating mac
 hine learning for accuracy and computational efficiency on different hardw
 are. SpeedyWeather.jl is designed for type flexibility with low precision\
 , and automatic differentiation to replace parts of the model with neural 
 networks for a more accurate representation of climate processes and compu
 tational efficiency.
LOCATION:Blue
URL:https://pretalx.com/juliacon-2022/talk/DZFPGX/
END:VEVENT
END:VCALENDAR