Team title: Ensemble Forecasts in Space WeatherJoin The Team

Team ID: S3-03

Team Leads:         

Jordan Guerra (Villanova University, USA), jordan.guerraaguilera@villanova.edu

Participants:

+ Click here to expand or collapse this section

Eric Adamson, Matthew Angling, Enrico Camporeale, Eelco Doornbus (co-lead), Galina Chikunova, Siegfried Gonzi, Carl Henney, Christina Kay, Ralf Keil, Matthew Lang, Steven Morley, Sophie Murray (co-lead), Mathew Owens, Nicholas Pedatella, Victor Pizzo, David Richardson, Daniel Welling

Keywords (impact): 

Keywords (activity type): Data Utilization, Assessment

Introduction:

Ensembles (which use a set of predictions to improve on a single-model output) have been very successful in improving operational weather forecasting and are also used in many other fields such as data science and economics. Ensemble techniques are even used in state-of-the-art machine learning competitions to improve performance. Their use in space weather forecasting could not only improve forecast accuracy but also provide simple model uncertainties that are crucial for improving end-user understanding of the products available.

Objectives:

The Testing, Understanding, and Leveraging Ensemble Predictions for Space weather (TULEPS) team was formed during a Lorentz Center Workshop in September 2019, with the main goal to make concrete steps towards improving space weather forecasting capabilities by implementing ensemble techniques that have been successful in other forecasting fields, especially terrestrial weather. Some specific topics of focus include

  • Usefulness of ensembles
  • Types of ensembles
  • Combinations of forecasts
  • Estimating uncertainty
  • Forecast evaluation

Action topics:

+ Click here to expand or collapse this section

Clusters with overlapping topics: 

Link to team external website:

https://www.lorentzcenter.nl/lc/web/2019/1195/info.php3?wsid=1195

https://github.com/TULEPS