One essential component of operational space weather forecasting is the prediction of solar eruptive events: flares, coronal mass ejections (CMEs), and their associated particle events. Whilst our understanding of the fundamental processes involved with solar eruptions has advanced in recent years with the advent of high-resolution spacecraft imaging, accurate forecasting of these events remains elusive. A multitude of flare forecasting methods are now available for operational use, however it is still unclear which of these methods performs best, and none are substantially better than climatological forecasts. Current operational space weather centres cannot rely on automated methods, and generally use statistical forecasts with a little human intervention.

Space weather researchers are increasingly looking towards methods used by the terrestrial weather community to improve prediction techniques. Ensemble forecasting has been used in numerical weather prediction for many years as a way to combine different predictions in order to obtain a more accurate result. It has proved useful in areas such as magnetospheric modelling and CME arrival analysis, however has not yet been implemented in operational flare forecasting. Here the results of combining several automated flare forecasting methods available at the NASA/CCMC Flare Scoreboard will be presented. A ‘best’ ensemble forecast is constructed based on what measure of performance is most important for the prediction. This method allows space weather forecasters the freedom to tailor the output to the needs of different end-users, and the resulting forecasts rival the accuracy of the human forecasts.

Most operational efforts currently focus on flare forecasts, considering the short warning time for impacts on Earth. This talk will also briefly highlight some recent progress on operational CME forecasting efforts, by combining results from the EU FP7 HELCATS and Horizon 2020 FLARECAST projects.