Ver-AI workshop on on Verification of AI-Based Meteorological Forecasts, Reading 2024

Several institutions have released global medium range meteorological forecasting models based on methods from machine learning, with training data provided by various reanalysis experiments. A proper and in-depth assessment of these models and the quality of their forecasts has yet to be carried out. Although in terms of simple and overall measures of skill such as mean square errors, AI-based forecasts clearly show very promising skill, we are just beginning to understand where and when these forecasts are useful and when not. Furthermore, while there is a well established methodology for verification of meteorological forecasts, it is not clear to what extent this methodology needs to be adapted or modified for AI based models. The objective of this workshop is to start this discussion and lay the groundwork for a methodology to assess the quality of AI-based forecasts.

Dates, Times: 24th of June 2024, 12 noon to 25th of June, 4pm

Venue: Room 1L61, Brian Hoskins Building, University of Reading.

Speakers: (see here for the full programme)

Simon Lang, ECMWF

Simon Driscoll, U Reading

Tobias Necker, U Vienna

Anna-Louise Ellis, MetOffice

Lewis Blunn, MetOffice

Zied Ben Bouallegue, ECMWF

Martin Leutbecher, ECMWF

Harris Sop Nkuiate, U Exeter

Etienne Roesch, U Reading

Cedric Mesnage, U Exeter

Registration:

University of Reading staff are free to attend. Registration is now closed for externals. Please email j.broecker@reading.ac.uk if you want to attend.

Travel Information

The Brian Hoskins building (aka Meteorology building) is building No~58 on this map of UoR Whiteknights campus. An excellent bus service runs from Reading station to Whiteknights campus with the Line 21 "Claret".

Organisers:

Jochen Bröcker and Simon Driscoll, University of Reading

Copyright © 2024, Jochen Bröcker