Anfragen und Hinweise auf weitere Veranstaltungen richten Sie bitte an: outreach(at)geomar.de
15.05.2023: online Ocean Circulation and Climate Dynamics Colloquium
Chiem van Straaten, Faculty of Science, Water and Climate Risk, Vrije Universiteit Amsterdam: "Machine Learning to improve and understand sub-seasonal forecasts of European temperature"
- online only-
When? Monday, 15 May 2023 at 11 am
Where? zoom https://geomar-de.zoom.us/j/82868320112?pwd=ZzdkUkpWMUhoeFlYcVB5LzJ5THhYZz09
Meeting ID: 828 6832 0112
Passcode: 708725
Abstract:
Europe faces droughts, heatwaves, and other extreme weather events every year. To prevent the worst of the impacts good probabilistic forecasts are needed, ideally issued several weeks in advance. In this presentation we explore whether physics-based, statistical and hybrid models can be used. Generally, sub-seasonal forecasts are difficult to make due to the chaotic evolution of the atmosphere. We however show that the division of warm and cold air over Europe can be predictable, as long as predictions are made for extended periods of time and large areas. The sources responsible for such predictability often lie in complex interactions between ocean, land and atmosphere. When disentangling these interactions with explainable Machine Learning, we learn that processes in the Pacific can be important for European summer weather. Subsequently, we evaluate ECMWF ensemble forecasts and show that large correctable errors relate to an erroneous simulation of this Pacific-to-Europe teleconnection. A correction of the physics-based forecasts with statistical post-processing increases sub-seasonal forecast skill for Europe in summer.