BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:WeatherGenerator Community Hackathon
DTSTART:20270126T080000Z
DTEND:20270128T170000Z
DTSTAMP:20260831T113200Z
UID:indico-event-582@events.ecmwf.int
CONTACT:events@ecmwf.int
DESCRIPTION:\nOverview\nThe WeatherGenerator will host its first Community
  Hackathon on 26–28 January 2027 in Jena\, Germany. This in-person\, han
 ds-on event will bring together researchers and professionals working acro
 ss  Earth System sciences to explore the WeatherGenertor\, exchange ideas
  and become part of its growing community. The goal is that each participa
 ting team can run and fine-tune the WeatherGenerator for its own applicati
 on while learning from and contributing to the community around the open-s
 ource model.\nFormat\nThe hackathon will open with an introduction and a t
 utorial on the WeatherGenerator core model\, its architecture\, training a
 pproach and data formats. This is followed by short presentations in which
  each team introduces its application. The remainder of the event is dedic
 ated to hands-on work on the applications\, supported throughout by core m
 odel developers and by application scientists from across the project. The
  hackathon concludes with final presentations from all teams on the aftern
 oon of the last day. A social programme will accompany the event.\nThe fir
 st day is expected to start at 09:00 CET on 26 January and end at 16:00 CE
 T on 28 January.\nAttendance\nRegistration opens on 1 September 2026 and w
 ill be moderated. Applications will be accepted on a rolling basis startin
 g 1 October 2026\, until capacity is reached. As places are limited\, earl
 y submission is encouraged.\nThe event is open to teams of two to five peo
 ple from research institutes\, national meteorological and hydrological se
 rvices\, agencies\, SMEs and industry\, working on weather\, climate\, wat
 er\, energy\, agriculture\, ecosystems or health. Teams from regions and a
 pplication areas that are currently underrepresented in machine-learning-b
 ased Earth system modelling are particularly encouraged to apply.\nTeam re
 quirements and preparation\nTeams are expected to arrive with a well-defin
 ed target application — for example weather forecasting for a particular
  country\, downscaling of a given variable over a defined region\, or pred
 icting an impact variable relevant to their sector. Data for the applicati
 on should be prepared in advance if possible. Technical guidance on data f
 ormats will be shared with teams after acceptance. Familiarity with Python
  and machine learning is expected\; though prior experience with foundatio
 n models and the WeatherGenerator is not.\nSupport and resources\nThe tuto
 rial and training material\, technical mentoring\, access to pretrained ch
 eckpoints and the compute resources needed to fine-tune the WeatherGenerat
 or during the event will all be provided by the project.\nCosts and travel
  support\nParticipation is free of charge but travel and accommodation is 
 self-funded. A limited number of travel grants may be available on a needs
 -based basis to support participants who could not otherwise attend\; inte
 rest can be indicated in the registration form. Invitation letters for vis
 a applications can be issued on request.\n \nMore details on the WeatherG
 enerator\, including further details on the hackathon and an overview of c
 urrent WeatherGenerator applications \n\nhttps://events.ecmwf.int/event/5
 82/
IMAGE;VALUE=URI:https://events.ecmwf.int/event/582/logo-3636154658.png
LOCATION:Jena
URL:https://events.ecmwf.int/event/582/
END:VEVENT
END:VCALENDAR