Essential Site Maintenance: Authorea-powered sites will be updated circa 15:00-17:00 Eastern on Tuesday 5 November.
There should be no interruption to normal services, but please contact us at [email protected] in case you face any issues.

loading page

Predicting Solar Flares using CNN and LSTM on Two Solar Cycles of Active Region Data
  • +5
  • Zeyu Sun,
  • Monica Bobra,
  • Xiantong Wang,
  • Yu Wang,
  • Hu Sun,
  • Tamas Gombosi,
  • Yang Chen,
  • Alfred Hero
Zeyu Sun
University of Michigan, University of Michigan, University of Michigan

Corresponding Author:[email protected]

Author Profile
Monica Bobra
Stanford University, Stanford University, Stanford University
Author Profile
Xiantong Wang
University of Michigan, University of Michigan, University of Michigan
Author Profile
Yu Wang
University of Michigan, University of Michigan, University of Michigan
Author Profile
Hu Sun
University of Michigan, University of Michigan, University of Michigan
Author Profile
Tamas Gombosi
University of Michigan, University of Michigan, University of Michigan
Author Profile
Yang Chen
University of Michigan, University of Michigan, University of Michigan
Author Profile
Alfred Hero
University of Michigan, University of Michigan, University of Michigan
Author Profile

Abstract

We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours. Using line-of-sight magnetograms and parameters of active regions in two data products covering Solar Cycle 23 and 24, we train and evaluate two deep learning algorithms—CNN and LSTM—and their stacking ensembles. The decisions of CNN are explained using visual attribution methods. We have the following three main findings. (1) LSTM trained on data from two solar cycles achieves significantly higher True Skill Scores (TSS) than that trained on data from a single solar cycle with a confidence level of at least 0.95. (2) On data from Solar Cycle 23, a stacking ensemble that combines predictions from LSTM and CNN using the TSS criterion achieves significantly higher TSS than the “select-best” strategy with a confidence level of at least 0.95. (3) A visual attribution method called Integrated Gradients is able to attribute the CNN’s predictions of flares to the emerging magnetic flux in the active region. It also reveals a limitation of CNN as a flare prediction method using line-of-sight magnetograms: it treats the polarity artifact of line-of-sight magnetograms as positive evidence of flares.