Deep neural networks of solar flare forecasting for complex active regions
Solar flare forecasting is one of major components of operational space weather forecasting. Complex active regions (ARs) are the main source producing major flares, but only a few studies are carried out to establish flare forecasting models for these ARs. In this study, four deep learning models,...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2023-06-01
|
Series: | Frontiers in Astronomy and Space Sciences |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fspas.2023.1177550/full |
_version_ | 1797796892424273920 |
---|---|
author | Ming Li Ming Li Ming Li Yanmei Cui Yanmei Cui Bingxian Luo Bingxian Luo Bingxian Luo Jingjing Wang Jingjing Wang Xin Wang Xin Wang Xin Wang |
author_facet | Ming Li Ming Li Ming Li Yanmei Cui Yanmei Cui Bingxian Luo Bingxian Luo Bingxian Luo Jingjing Wang Jingjing Wang Xin Wang Xin Wang Xin Wang |
author_sort | Ming Li |
collection | DOAJ |
description | Solar flare forecasting is one of major components of operational space weather forecasting. Complex active regions (ARs) are the main source producing major flares, but only a few studies are carried out to establish flare forecasting models for these ARs. In this study, four deep learning models, called Complex Active Region Flare Forecasting Model (CARFFM)-1, −2, −3, and −4, are established. They take AR longitudinal magnetic fields, AR vector magnetic fields, AR longitudinal magnetic fields and the total unsigned magnetic flux in the neutral line region, AR vector magnetic fields and the total unsigned magnetic flux in the neutral region as input, respectively. These four models can predict the production of M-class or above flares in the complex ARs for the next 48 h. Through comparing the performance of the models, CARFFM-4 has the best forecasting ability, which has the most abundant input information. It is suggested that more valuable and rich input can improve the model performance. |
first_indexed | 2024-03-13T03:39:54Z |
format | Article |
id | doaj.art-d6413415f9e2423f9801c8c701f81b0c |
institution | Directory Open Access Journal |
issn | 2296-987X |
language | English |
last_indexed | 2024-03-13T03:39:54Z |
publishDate | 2023-06-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Astronomy and Space Sciences |
spelling | doaj.art-d6413415f9e2423f9801c8c701f81b0c2023-06-23T10:49:42ZengFrontiers Media S.A.Frontiers in Astronomy and Space Sciences2296-987X2023-06-011010.3389/fspas.2023.11775501177550Deep neural networks of solar flare forecasting for complex active regionsMing Li0Ming Li1Ming Li2Yanmei Cui3Yanmei Cui4Bingxian Luo5Bingxian Luo6Bingxian Luo7Jingjing Wang8Jingjing Wang9Xin Wang10Xin Wang11Xin Wang12State Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness Chinese Academy of Sciences, Beijing, ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, ChinaUniversity of Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Science and Technology on Environmental Space Situation Awareness Chinese Academy of Sciences, Beijing, ChinaSolar flare forecasting is one of major components of operational space weather forecasting. Complex active regions (ARs) are the main source producing major flares, but only a few studies are carried out to establish flare forecasting models for these ARs. In this study, four deep learning models, called Complex Active Region Flare Forecasting Model (CARFFM)-1, −2, −3, and −4, are established. They take AR longitudinal magnetic fields, AR vector magnetic fields, AR longitudinal magnetic fields and the total unsigned magnetic flux in the neutral line region, AR vector magnetic fields and the total unsigned magnetic flux in the neutral region as input, respectively. These four models can predict the production of M-class or above flares in the complex ARs for the next 48 h. Through comparing the performance of the models, CARFFM-4 has the best forecasting ability, which has the most abundant input information. It is suggested that more valuable and rich input can improve the model performance.https://www.frontiersin.org/articles/10.3389/fspas.2023.1177550/fullflare forecastingcomplex active regionsdeep learningvector fieldthe total unsigned magnetic flux |
spellingShingle | Ming Li Ming Li Ming Li Yanmei Cui Yanmei Cui Bingxian Luo Bingxian Luo Bingxian Luo Jingjing Wang Jingjing Wang Xin Wang Xin Wang Xin Wang Deep neural networks of solar flare forecasting for complex active regions Frontiers in Astronomy and Space Sciences flare forecasting complex active regions deep learning vector field the total unsigned magnetic flux |
title | Deep neural networks of solar flare forecasting for complex active regions |
title_full | Deep neural networks of solar flare forecasting for complex active regions |
title_fullStr | Deep neural networks of solar flare forecasting for complex active regions |
title_full_unstemmed | Deep neural networks of solar flare forecasting for complex active regions |
title_short | Deep neural networks of solar flare forecasting for complex active regions |
title_sort | deep neural networks of solar flare forecasting for complex active regions |
topic | flare forecasting complex active regions deep learning vector field the total unsigned magnetic flux |
url | https://www.frontiersin.org/articles/10.3389/fspas.2023.1177550/full |
work_keys_str_mv | AT mingli deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT mingli deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT mingli deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT yanmeicui deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT yanmeicui deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT bingxianluo deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT bingxianluo deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT bingxianluo deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT jingjingwang deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT jingjingwang deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT xinwang deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT xinwang deepneuralnetworksofsolarflareforecastingforcomplexactiveregions AT xinwang deepneuralnetworksofsolarflareforecastingforcomplexactiveregions |