Solar Flare Intensity Prediction With Machine Learning Models
Abstract 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 Regi...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-07-01
|
| Series: | Space Weather |
| Online Access: | https://doi.org/10.1029/2020SW002440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536425581871104 |
|---|---|
| author | Zhenbang Jiao Hu Sun Xiantong Wang Ward Manchester Tamas Gombosi Alfred Hero Yang Chen |
| author_facet | Zhenbang Jiao Hu Sun Xiantong Wang Ward Manchester Tamas Gombosi Alfred Hero Yang Chen |
| author_sort | Zhenbang Jiao |
| collection | DOAJ |
| description | Abstract 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, https://doi.org/10.1029/2019SW002214). 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. |
| format | Article |
| id | doaj-art-a402f9860cb04362a4a817ec9cf6c8fe |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2020-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-a402f9860cb04362a4a817ec9cf6c8fe2025-01-14T16:30:52ZengWileySpace Weather1542-73902020-07-01187n/an/a10.1029/2020SW002440Solar Flare Intensity Prediction With Machine Learning ModelsZhenbang Jiao0Hu Sun1Xiantong Wang2Ward Manchester3Tamas Gombosi4Alfred Hero5Yang Chen6Department of Statistics University of Michigan Ann Arbor MI USADepartment of Statistics University of Michigan Ann Arbor MI USAClimate and Space Sciences and Engineering University of Michigan Ann Arbor MI USAClimate and Space Sciences and Engineering University of Michigan Ann Arbor MI USAClimate and Space Sciences and Engineering University of Michigan Ann Arbor MI USADepartment of Statistics University of Michigan Ann Arbor MI USADepartment of Statistics University of Michigan Ann Arbor MI USAAbstract 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, https://doi.org/10.1029/2019SW002214). 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.https://doi.org/10.1029/2020SW002440 |
| spellingShingle | Zhenbang Jiao Hu Sun Xiantong Wang Ward Manchester Tamas Gombosi Alfred Hero Yang Chen Solar Flare Intensity Prediction With Machine Learning Models Space Weather |
| title | Solar Flare Intensity Prediction With Machine Learning Models |
| title_full | Solar Flare Intensity Prediction With Machine Learning Models |
| title_fullStr | Solar Flare Intensity Prediction With Machine Learning Models |
| title_full_unstemmed | Solar Flare Intensity Prediction With Machine Learning Models |
| title_short | Solar Flare Intensity Prediction With Machine Learning Models |
| title_sort | solar flare intensity prediction with machine learning models |
| url | https://doi.org/10.1029/2020SW002440 |
| work_keys_str_mv | AT zhenbangjiao solarflareintensitypredictionwithmachinelearningmodels AT husun solarflareintensitypredictionwithmachinelearningmodels AT xiantongwang solarflareintensitypredictionwithmachinelearningmodels AT wardmanchester solarflareintensitypredictionwithmachinelearningmodels AT tamasgombosi solarflareintensitypredictionwithmachinelearningmodels AT alfredhero solarflareintensitypredictionwithmachinelearningmodels AT yangchen solarflareintensitypredictionwithmachinelearningmodels |