ECWMF Job Alert: Scientist - Uncertainty Quantification for Destination Earth

ECMWF has an exciting opportunity for a Scientist (A2) to help shape and deliver Destination Earth (DestinE) developments, by making use of machine learning techniques and statistical methods. You will apply powerful data processing techniques based on machine learning and statistical methods to support the uncertainty quantification for the Digital Twin for weather induced extremes. This Digital Twin will rely on high-resolution (km-scale) simulations produced with ECMWF’s Integrated Forecasting System (IFS) to drive much enhanced weather-induced extremes predictions.

Uncertainty quantification is particularly essential for the prediction of extreme events, where it is important to know whether there is even a slight chance of an event occurring. Operationally, most weather centres (including ECMWF) run ensemble forecasts generating an array of equally likely forecasts, given assumptions about the uncertainty in the observations and models. However, for the resolutions and data volumes envisaged in DestinE, running large ensembles in a timely manner will be very difficult. Machine learning offers new levels of complex data processing that can enhance the representation of uncertainty and complement ensemble methods by, for example, blending ensemble members from different physical and data-driven models or generating new members.

You will join an existing group at ECMWF working on applying machine learning and statistical techniques to improve various aspects of the ECMWF modelling and operational workflows, and will make the link between these efforts and similar efforts in DestinE. You will also contribute to regular progress reports to the European Commission.

More info here