Implementation paradigm for supervised flare forecasting studies: A deep learning application with video data
Open Access
- 24 June 2022
- journal article
- research article
- Published by EDP Sciences in Astronomy & Astrophysics
- Vol. 662, A105
Abstract
Aims. In this study, we introduce a general paradigm for generating independent and well-balanced training, validation, and test sets for use in supervised machine and deep learning flare forecasting, to determine the extent to which video-based deep learning can predict solar flares. Methods. We use this implementation paradigm in the case of a deep neural network, which takes videos of magnetograms recorded by the Helioseismic and Magnetic Imager onboard the Solar Dynamics Observatory (SDO/HMI) as input. Results. The way the training and validation sets are prepared for network optimization has a significant impact on the prediction performances. Furthermore, deep learning is able to realize flare video classification with prediction performances that are in line with those obtained by machine learning approaches that require an a priori extraction of features from the HMI magnetograms. Conclusions. To our knowledge, this is the first time that the solar flare forecasting problem is addressed by means of a deep neural network for video classification, which does not require any a priori extraction of features from the HMI magnetograms.Keywords
All Related Versions
Funding Information
- AI-FLARES ASI-INAF (2018-16-HH.0)
This publication has 41 references indexed in Scilit:
- Validation of the NOAA Space Weather Prediction Center's solar flare forecasting look‐up table and forecaster‐issued probabilitiesSpace Weather, 2012
- TOWARD RELIABLE BENCHMARKING OF SOLAR FLARE FORECASTING METHODSThe Astrophysical Journal Letters, 2012
- Global Properties of Solar FlaresSpace Science Reviews, 2011
- TESTING AUTOMATED SOLAR FLARE FORECASTING WITH 13 YEARS OF MICHELSON DOPPLER IMAGER MAGNETOGRAMSThe Astrophysical Journal, 2010
- Turbulence, complexity, and solar flaresAdvances In Space Research, 2010
- Keynote address: Outstanding problems in solar physicsJournal of Astrophysics and Astronomy, 2008
- Evidence for Magnetic Reconnection in Three Homologous Solar Flares Observed byRHESSIThe Astrophysical Journal, 2004
- Long Short-Term MemoryNeural Computation, 1997
- New observational facts about solar flares from Yohkoh studies — Evidence of magnetic reconnection and a unified model of flaresAdvances In Space Research, 1996
- Cosmic flare transients - Constraints upon models for energy storage and release derived from the event frequency distributionThe Astrophysical Journal, 1978