Solar Flare Intensity Prediction With Machine Learning Models
-
- Zhenbang Jiao
- Department of Statistics University of Michigan Ann Arbor MI USA
-
- Hu Sun
- Department of Statistics University of Michigan Ann Arbor MI USA
-
- Xiantong Wang
- Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
-
- Ward Manchester
- Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
-
- Tamas Gombosi
- Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USA
-
- Alfred Hero
- Department of Statistics University of Michigan Ann Arbor MI USA
-
- Yang Chen
- Department of Statistics University of Michigan Ann Arbor MI USA
書誌事項
- 公開日
- 2020-07
- 権利情報
-
- http://creativecommons.org/licenses/by-nc-nd/4.0/
- DOI
-
- 10.1029/2020sw002440
- 公開者
- American Geophysical Union (AGU)
この論文をさがす
説明
<jats:title>Abstract</jats:title><jats:p>We develop a mixed long short‐term memory (LSTM) regression model to predict the maximum solar flare intensity within a 24‐hr time window 0–24, 6–30, 12–36, and 24–48 hr ahead of time using 6, 12, 24, and 48 hr of data (predictors) for each Helioseismic and Magnetic Imager (HMI) Active Region Patch (HARP). The model makes use of (1) the Space‐Weather HMI Active Region Patch (SHARP) parameters as predictors and (2) the exact flare intensities instead of class labels recorded in the Geostationary Operational Environmental Satellites (GOES) data set, which serves as the source of the response variables. Compared to solar flare classification, the model offers us more detailed information about the exact maximum flux level, that is, intensity, for each occurrence of a flare. We also consider classification models built on top of the regression model and obtain better results in solar flare classifications as compared to Chen et al. (2019, <jats:ext-link xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="https://doi.org/10.1029/2019SW002214">https://doi.org/10.1029/2019SW002214</jats:ext-link>). Our results suggest that the most efficient time period for predicting the solar activity is within 24 hr before the prediction time using the SHARP parameters and the LSTM model.</jats:p>
収録刊行物
-
- Space Weather
-
Space Weather 18 (7), e2020SW002440-, 2020-07
American Geophysical Union (AGU)
