Ensemble Forecasting of Major Solar Flares: Methods for Combining Models

TL;DR

This paper develops a linear ensemble forecasting method for major solar flares by combining multiple models, improving prediction skill by 5-15% over individual models and outperforming equal-weight averages in most cases.

Contribution

It introduces a simple multi-model linear ensemble approach for solar flare prediction, enhancing forecast accuracy and providing a flexible framework for operational space weather centers.

Findings

Most ensembles outperform individual models by 5-15% in skill metrics.

Over 90% of ensembles perform better than equal-weight averages.

Forecast uncertainties are less than 20% for probabilities above 0.2.

Abstract

One essential component of operational space weather forecasting is the prediction of solar flares. With a multitude of flare forecasting methods now available online it is still unclear which of these methods performs best, and none are substantially better than climatological forecasts. Space weather researchers are increasingly looking towards methods used by the terrestrial weather community to improve current forecasting 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. Here we construct ensemble forecasts for major solar flares by linearly combining the full-disk probabilistic forecasts from a group of operational forecasting methods (ASAP, ASSA, MAG4, MOSWOC, NOAA, and MCSTAT). Forecasts from each method are weighted by a factor that accounts for the method's ability to predict previous events, and several performance metrics (both probabilistic and categorical) are considered. It is found that most ensembles achieve a better skill metric (between 5\% and 15\%) than any of the members alone. Moreover, over 90\% of ensembles perform better (as measured by forecast attributes) than a simple equal-weights average. Finally, ensemble uncertainties are highly dependent on the internal metric being optimized and they are estimated to be less than 20\% for probabilities greater than 0.2. This simple multi-model, linear ensemble technique can provide operational space weather centres with the basis for constructing a versatile ensemble forecasting system -- an improved starting point to their forecasts that can be tailored to different end-user needs.