Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters

  • Yang Chen
    Department of Statistics University of Michigan Ann Arbor MI USA
  • Ward B. Manchester
    Department of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
  • Alfred O. Hero
    Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA
  • Gabor Toth
    Department of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
  • Benoit DuFumier
    Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA
  • Tian Zhou
    Department of Statistics University of Michigan Ann Arbor MI USA
  • Xiantong Wang
    Department of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
  • Haonan Zhu
    Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA
  • Zeyu Sun
    Department of Electrical Engineering and Computer Science University of Michigan Ann Arbor MI USA
  • Tamas I. Gombosi
    Department of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA

書誌事項

公開日
2019-10
権利情報
  • http://onlinelibrary.wiley.com/termsAndConditions#am
  • http://onlinelibrary.wiley.com/termsAndConditions#vor
DOI
  • 10.1029/2019sw002214
公開者
American Geophysical Union (AGU)

この論文をさがす

説明

<jats:title>Abstract</jats:title><jats:p>In this paper we present several methods to identify precursors that show great promise for early predictions of solar flare events. A data preprocessing pipeline is built to extract useful data from multiple sources, Geostationary Operational Environmental Satellites and Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI), to prepare inputs for machine learning algorithms. Two classification models are presented: classification of flares from quiet times for active regions and classification of strong versus weak flare events. We adopt deep learning algorithms to capture both spatial and temporal information from HMI magnetogram data. Effective feature extraction and feature selection with raw magnetogram data using deep learning and statistical algorithms enable us to train classification models to achieve almost as good performance as using active region parameters provided in HMI/Space‐Weather HMI‐Active Region Patch (SHARP) data files. Case studies show a significant increase in the prediction score around 20 hr before strong solar flare events.</jats:p>

収録刊行物

  • Space Weather

    Space Weather 17 (10), 1404-1426, 2019-10

    American Geophysical Union (AGU)

被引用文献 (1)*注記

もっと見る

問題の指摘

ページトップへ