A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast
This work addresses the need for reliable, high-frequency forecasts in space weather science to avoid overlearning and enable experimental performance measurement.
The authors tackled the problem of real-time solar flare forecasting by operating an automated service that provides 24-hour-ahead predictions every 12 minutes, reporting on the method and results.
Automated forecasts serve important role in space weather science, by providing statistical insights to flare-trigger mechanisms, and by enabling tailor-made forecasts and high-frequency forecasts. Only by realtime forecast we can experimentally measure the performance of flare-forecasting methods while confidently avoiding overlearning. We have been operating unmanned flare forecast service since August, 2015 that provides 24-hour-ahead forecast of solar flares, every 12 minutes. We report the method and prediction results of the system.