Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning
This study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider photospheric solar magnetic fields as input, and...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | The Astrophysical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-4357/acbd3c |
| _version_ | 1797699364688232448 |
|---|---|
| author | Sumiaya Rahman Seungheon Shin Hyun-Jin Jeong Ashraf Siddique Yong-Jae Moon Eunsu Park Jihye Kang Sung-Ho Bae |
| author_facet | Sumiaya Rahman Seungheon Shin Hyun-Jin Jeong Ashraf Siddique Yong-Jae Moon Eunsu Park Jihye Kang Sung-Ho Bae |
| author_sort | Sumiaya Rahman |
| collection | DOAJ |
| description | This study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider photospheric solar magnetic fields as input, and electron density distribution simulated with the MHD Algorithm outside a Sphere (MAS) at a given solar radius is taken as output. We consider 155 pairs of Carrington rotations as inputs and outputs from 2010 June to 2022 April for training and testing. We train 152 deep-learning models for 152 solar radii, which are taken up to 30 solar radii. The artificial intelligence (AI) generated 3D electron densities from this study are quite consistent with the simulated ones from lower radii to higher radii, with an average correlation coefficient 0.97. The computing time of testing data sets up to 30 solar radii of 152 deep-learning models is about 45.2 s using the NVIDIA TITAN XP graphics-processing unit, which is much less than the typical simulation time of MAS. We find that the synthetic coronagraphic images estimated from the deep-learning models are similar to the Solar Heliospheric Observatory (SOHO)/Large Angle and Spectroscopic Coronagraph C3 coronagraph data, especially during the solar minimum period. The AI-generated coronal density distribution from this study can be used for space weather models on a near-real-time basis. |
| first_indexed | 2024-03-12T04:08:05Z |
| format | Article |
| id | doaj.art-a21885a2e382407d9893b07256f0217d |
| institution | Directory Open Access Journal |
| issn | 1538-4357 |
| language | English |
| last_indexed | 2024-03-12T04:08:05Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal |
| spelling | doaj.art-a21885a2e382407d9893b07256f0217d2023-09-03T11:13:53ZengIOP PublishingThe Astrophysical Journal1538-43572023-01-0194812110.3847/1538-4357/acbd3cFast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep LearningSumiaya Rahman0Seungheon Shin1https://orcid.org/0000-0002-5144-8230Hyun-Jin Jeong2https://orcid.org/0000-0003-4616-947XAshraf Siddique3https://orcid.org/0000-0003-2186-5735Yong-Jae Moon4https://orcid.org/0000-0001-6216-6944Eunsu Park5https://orcid.org/0000-0003-0969-286XJihye Kang6https://orcid.org/0000-0001-6213-4088Sung-Ho Bae7https://orcid.org/0000-0003-2677-3186School of Space Research, Kyung Hee University , Yongin, 17104, Republic of Korea ; moonyj@khu.ac.krSchool of Space Research, Kyung Hee University , Yongin, 17104, Republic of Korea ; moonyj@khu.ac.kr; Earth Intelligence Division, SI Analytics, Daejeon, 34047, Republic of KoreaDepartment of Astronomy and Space Science, College of Applied Science, Kyung Hee University , Yongin, 17104, Republic of KoreaDepartment of Computer Science Engineering, Kyung Hee University , Yongin, 17104, Republic of KoreaSchool of Space Research, Kyung Hee University , Yongin, 17104, Republic of Korea ; moonyj@khu.ac.kr; Department of Astronomy and Space Science, College of Applied Science, Kyung Hee University , Yongin, 17104, Republic of KoreaSpace Science Division, Korea Astronomy and Space Science Institute , Daejeon, 34055, Republic of KoreaDepartment of Astronomy and Space Science, College of Applied Science, Kyung Hee University , Yongin, 17104, Republic of KoreaDepartment of Computer Science Engineering, College of Software, Kyung Hee University , Yongin, 17104, Republic of KoreaThis study is the first attempt to generate a three-dimensional (3D) coronal electron density distribution based on the pix2pixHD model, whose computing time is much shorter than that of the magnetohydrodynamic (MHD) simulation. For this, we consider photospheric solar magnetic fields as input, and electron density distribution simulated with the MHD Algorithm outside a Sphere (MAS) at a given solar radius is taken as output. We consider 155 pairs of Carrington rotations as inputs and outputs from 2010 June to 2022 April for training and testing. We train 152 deep-learning models for 152 solar radii, which are taken up to 30 solar radii. The artificial intelligence (AI) generated 3D electron densities from this study are quite consistent with the simulated ones from lower radii to higher radii, with an average correlation coefficient 0.97. The computing time of testing data sets up to 30 solar radii of 152 deep-learning models is about 45.2 s using the NVIDIA TITAN XP graphics-processing unit, which is much less than the typical simulation time of MAS. We find that the synthetic coronagraphic images estimated from the deep-learning models are similar to the Solar Heliospheric Observatory (SOHO)/Large Angle and Spectroscopic Coronagraph C3 coronagraph data, especially during the solar minimum period. The AI-generated coronal density distribution from this study can be used for space weather models on a near-real-time basis.https://doi.org/10.3847/1538-4357/acbd3cThe SunSolar photosphereAstronomy data analysisAstronomy image processing |
| spellingShingle | Sumiaya Rahman Seungheon Shin Hyun-Jin Jeong Ashraf Siddique Yong-Jae Moon Eunsu Park Jihye Kang Sung-Ho Bae Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning The Astrophysical Journal The Sun Solar photosphere Astronomy data analysis Astronomy image processing |
| title | Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning |
| title_full | Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning |
| title_fullStr | Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning |
| title_full_unstemmed | Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning |
| title_short | Fast Reconstruction of 3D Density Distribution around the Sun Based on the MAS by Deep Learning |
| title_sort | fast reconstruction of 3d density distribution around the sun based on the mas by deep learning |
| topic | The Sun Solar photosphere Astronomy data analysis Astronomy image processing |
| url | https://doi.org/10.3847/1538-4357/acbd3c |
| work_keys_str_mv | AT sumiayarahman fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT seungheonshin fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT hyunjinjeong fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT ashrafsiddique fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT yongjaemoon fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT eunsupark fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT jihyekang fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning AT sunghobae fastreconstructionof3ddensitydistributionaroundthesunbasedonthemasbydeeplearning |