BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Webinar: Anemoi - a framework for building the AIFS and other data
 -driven weather forecasting models
DTSTART:20240430T080000Z
DTEND:20240430T090000Z
DTSTAMP:20261007T123100Z
UID:indico-event-409@events.ecmwf.int
CONTACT:training@ecmwf.int
DESCRIPTION:PresenterMatthew Chantry\, ECMWFDescriptionLast year ECMWF int
 roduced the AIFS\, building on a series of innovative papers which demonst
 rated the potential of machine learning in creating data-driven weather fo
 recasting models.Machine learning models typically build on open-source fr
 ameworks\, such as Tensorflow\, PyTorch and JAX which allow communities to
  work together and build on one another's work. Weather forecasting brings
  its own challenges for machine learning\, with large datasets and spatial
 -temporal problems.In this webinar\, we will introduce Anemoi\, the toolbo
 x from which the AIFS is trained. We have been developing this toolbox wi
 th a view to many users both inside and outside of ECMWF to use the toolbo
 x to train both global and local weather forecasting models. The toolbox a
 ims to allow users to bring their own datasets and customise their ML mode
 ls.We will introduce the toolbox\, talk through the steps needed to train 
 a data-driven model and explain how Anemoi helps with these tasks. Finally
  we will outline a roadmap for future Anemoi development.AttendancePlease 
 note that this webinar is open to employees of ECMWF Member and Co-operati
 ng States' Meteorological services. If you would like to attend the webin
 ar\, please complete the registration form in the left-hand side menu. We 
 will alert you of your acceptance to the webinar and send you all the join
 ing information and Microsoft Teams meeting details in due course. A recor
 ding will be available for those unable to attend the event.The webinar wi
 ll be conducted in English.\n\nhttps://events.ecmwf.int/event/409/
LOCATION:Virtual
URL:https://events.ecmwf.int/event/409/
END:VEVENT
END:VCALENDAR