BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Data-driven ocean modelling   - Rachel Furner\, British Antarcti
 c Survey / ECMWF
DTSTART:20241206T140000Z
DTEND:20241206T150000Z
UID:TALK224698@talks.cam.ac.uk
CONTACT:Dr Yohei Takano
DESCRIPTION:Data-driven models are becoming increasingly competent at task
 s fundamental to weather and climate prediction. Relative to machine learn
 ing (ML) based atmospheric models\, which have shown promise in short-term
  forecasting\, ML-based ocean forecasting remains less explored.  \nIn thi
 s seminar we first present results from idealised experiments\; training a
  UNet to emulate a GCM with a simplified channel model configuration. We s
 how that interactions with land are especially challenging. This systemati
 c bias highlights the need for careful and thorough model assessment\, and
  emphasises one of the many differences between modelling the atmosphere a
 nd the ocean. \nWe then present work developing an ocean component for a d
 ata-driven earth system model\, based on the AIFS weather prediction model
  developed at ECMWF. We give an overview of the AIFS weather prediction sy
 stem\, and then highlight the various design considerations in developing 
 a data-driven earth system model and show preliminary results from this wo
 rk.  
LOCATION:BAS Seminar Room 2
END:VEVENT
END:VCALENDAR