A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast

Yuko Hada-Muranushi; Takayuki Muranushi; Ayumi Asai; Daisuke Okanohara; Rudy Raymond; Gentaro Watanabe; Shigeru Nemoto; Kazunari Shibata

A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast

Solar and Stellar Astrophysics 2016-06-07 v1 Machine Learning

Authors: Yuko Hada-Muranushi , Takayuki Muranushi , Ayumi Asai , Daisuke Okanohara , Rudy Raymond , Gentaro Watanabe , Shigeru Nemoto , Kazunari Shibata

View on arXiv ↗ PDF ↗

Abstract

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.

Keywords

solar flare forecast deep learning automated realtime forecast space weather flare-trigger mechanisms overlearning

Cite

@article{arxiv.1606.01587,
  title  = {A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast},
  author = {Yuko Hada-Muranushi and Takayuki Muranushi and Ayumi Asai and Daisuke Okanohara and Rudy Raymond and Gentaro Watanabe and Shigeru Nemoto and Kazunari Shibata},
  journal= {arXiv preprint arXiv:1606.01587},
  year   = {2016}
}

Comments

6 pages, 4 figures

A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast

Abstract

Keywords

Cite

Comments

Related papers