Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23
Abstract We use machine learning methods to predict whether an active region (AR) which produces flares will lead to a solar energetic particle (SEP) event using Space‐Weather Michelson Doppler Imager (MDI) Active Region Patches (SMARPs). This new data product is derived from maps of the solar surfa...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-02-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2021SW002842 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536365554040832 |
|---|---|
| author | Spiridon Kasapis Lulu Zhao Yang Chen Xiantong Wang Monica Bobra Tamas Gombosi |
| author_facet | Spiridon Kasapis Lulu Zhao Yang Chen Xiantong Wang Monica Bobra Tamas Gombosi |
| author_sort | Spiridon Kasapis |
| collection | DOAJ |
| description | Abstract We use machine learning methods to predict whether an active region (AR) which produces flares will lead to a solar energetic particle (SEP) event using Space‐Weather Michelson Doppler Imager (MDI) Active Region Patches (SMARPs). This new data product is derived from maps of the solar surface magnetic field taken by the MDI aboard the Solar and Heliospheric Observatory. We survey the SMARP active regions associated with flares that appear on the solar disk between 5 June 1996 and 14 August 2010, label those that produced SEPs as positive and the rest as negative. The AR SMARP features that correspond to each flare are used to train two different types of machine learning methods, the support vector machines (SVMs) and the regression models. The results show that the SMARP data can predict whether a flare will lead to an SEP with accuracy (ACC) ≤0.72 ± 0.12 while allowing for a competitive leading time of 55.3 ± 28.6 min for forecasting the SEP events. |
| format | Article |
| id | doaj-art-d9ceebb7d7af439ca28fdf7499713531 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-02-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-d9ceebb7d7af439ca28fdf74997135312025-01-14T16:30:59ZengWileySpace Weather1542-73902022-02-01202n/an/a10.1029/2021SW002842Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23Spiridon Kasapis0Lulu Zhao1Yang Chen2Xiantong Wang3Monica Bobra4Tamas Gombosi5Department of Naval Architecture and Marine Engineering University of Michigan Ann Arbor MI USADepartment of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USADepartment of Statistics University of Michigan Ann Arbor MI USADepartment of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USAHansen Experimental Physics Laboratory Stanford University Stanford CA USADepartment of Climate and Space Sciences and Engineering University of Michigan Ann Arbor MI USAAbstract We use machine learning methods to predict whether an active region (AR) which produces flares will lead to a solar energetic particle (SEP) event using Space‐Weather Michelson Doppler Imager (MDI) Active Region Patches (SMARPs). This new data product is derived from maps of the solar surface magnetic field taken by the MDI aboard the Solar and Heliospheric Observatory. We survey the SMARP active regions associated with flares that appear on the solar disk between 5 June 1996 and 14 August 2010, label those that produced SEPs as positive and the rest as negative. The AR SMARP features that correspond to each flare are used to train two different types of machine learning methods, the support vector machines (SVMs) and the regression models. The results show that the SMARP data can predict whether a flare will lead to an SEP with accuracy (ACC) ≤0.72 ± 0.12 while allowing for a competitive leading time of 55.3 ± 28.6 min for forecasting the SEP events.https://doi.org/10.1029/2021SW002842solar energetic particlesforecastSMARPmachine learningsolar flaresprediction |
| spellingShingle | Spiridon Kasapis Lulu Zhao Yang Chen Xiantong Wang Monica Bobra Tamas Gombosi Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 Space Weather solar energetic particles forecast SMARP machine learning solar flares prediction |
| title | Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 |
| title_full | Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 |
| title_fullStr | Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 |
| title_full_unstemmed | Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 |
| title_short | Interpretable Machine Learning to Forecast SEP Events for Solar Cycle 23 |
| title_sort | interpretable machine learning to forecast sep events for solar cycle 23 |
| topic | solar energetic particles forecast SMARP machine learning solar flares prediction |
| url | https://doi.org/10.1029/2021SW002842 |
| work_keys_str_mv | AT spiridonkasapis interpretablemachinelearningtoforecastsepeventsforsolarcycle23 AT luluzhao interpretablemachinelearningtoforecastsepeventsforsolarcycle23 AT yangchen interpretablemachinelearningtoforecastsepeventsforsolarcycle23 AT xiantongwang interpretablemachinelearningtoforecastsepeventsforsolarcycle23 AT monicabobra interpretablemachinelearningtoforecastsepeventsforsolarcycle23 AT tamasgombosi interpretablemachinelearningtoforecastsepeventsforsolarcycle23 |