Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models
Coronal mass ejections (CMEs) are massive solar eruptions, which have a significant impact on Earth. In this paper, we propose a new method, called DeepCME, to estimate two properties of CMEs, namely, CME mass and kinetic energy. Being able to estimate these properties helps better understand CME dy...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | The Astrophysical Journal Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/2041-8213/ad0c4a |
| _version_ | 1827630575045836800 |
|---|---|
| author | Khalid A. Alobaid Yasser Abduallah Jason T. L. Wang Haimin Wang Shen Fan Jialiang Li Huseyin Cavus Vasyl Yurchyshyn |
| author_facet | Khalid A. Alobaid Yasser Abduallah Jason T. L. Wang Haimin Wang Shen Fan Jialiang Li Huseyin Cavus Vasyl Yurchyshyn |
| author_sort | Khalid A. Alobaid |
| collection | DOAJ |
| description | Coronal mass ejections (CMEs) are massive solar eruptions, which have a significant impact on Earth. In this paper, we propose a new method, called DeepCME, to estimate two properties of CMEs, namely, CME mass and kinetic energy. Being able to estimate these properties helps better understand CME dynamics. Our study is based on the CME catalog maintained at the Coordinated Data Analysis Workshops Data Center, which contains all CMEs manually identified since 1996 using the Large Angle and Spectrometric Coronagraph (LASCO) on board the Solar and Heliospheric Observatory. We use LASCO C2 data in the period between 1996 January and 2020 December to train, validate, and test DeepCME through 10-fold cross validation. The DeepCME method is a fusion of three deep-learning models, namely ResNet, InceptionNet, and InceptionResNet. Our fusion model extracts features from LASCO C2 images, effectively combining the learning capabilities of the three component models to jointly estimate the mass and kinetic energy of CMEs. Experimental results show that the fusion model yields a mean relative error (MRE) of 0.013 (0.009, respectively) compared to the MRE of 0.019 (0.017, respectively) of the best component model InceptionResNet (InceptionNet, respectively) in estimating the CME mass (kinetic energy, respectively). To our knowledge, this is the first time that deep learning has been used for CME mass and kinetic energy estimations. |
| first_indexed | 2024-03-09T14:08:39Z |
| format | Article |
| id | doaj.art-45cefac69083427d92dca68f9a91f8c9 |
| institution | Directory Open Access Journal |
| issn | 2041-8205 |
| language | English |
| last_indexed | 2024-03-09T14:08:39Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astrophysical Journal Letters |
| spelling | doaj.art-45cefac69083427d92dca68f9a91f8c92023-11-29T15:46:55ZengIOP PublishingThe Astrophysical Journal Letters2041-82052023-01-019582L3410.3847/2041-8213/ad0c4aEstimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning ModelsKhalid A. Alobaid0https://orcid.org/0009-0007-4731-2772Yasser Abduallah1https://orcid.org/0000-0003-0792-2270Jason T. L. Wang2https://orcid.org/0000-0002-2486-1097Haimin Wang3https://orcid.org/0000-0002-5233-565XShen Fan4Jialiang Li5Huseyin Cavus6https://orcid.org/0000-0003-4224-7039Vasyl Yurchyshyn7https://orcid.org/0000-0001-9982-2175Institute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Department of Computer Science, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA; College of Applied Computer Sciences, King Saud University , Riyadh 11451, Saudi ArabiaInstitute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Department of Computer Science, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USAInstitute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Department of Computer Science, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USAInstitute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Center for Solar-Terrestrial Research, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA; Big Bear Solar Observatory, New Jersey Institute of Technology , 40386 North Shore Lane, Big Bear City, CA 92314, USAInstitute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Department of Computer Science, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USAInstitute for Space Weather Sciences, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USA ; kaa65@njit.edu; Department of Computer Science, New Jersey Institute of Technology, University Heights , Newark, NJ 07102, USADepartment of Physics, Canakkale Onsekiz Mart University , 17110 Canakkale, Turkey; Harvard-Smithsonian Center for Astrophysics , 60 Garden Street, Cambridge, MA 02138, USABig Bear Solar Observatory, New Jersey Institute of Technology , 40386 North Shore Lane, Big Bear City, CA 92314, USACoronal mass ejections (CMEs) are massive solar eruptions, which have a significant impact on Earth. In this paper, we propose a new method, called DeepCME, to estimate two properties of CMEs, namely, CME mass and kinetic energy. Being able to estimate these properties helps better understand CME dynamics. Our study is based on the CME catalog maintained at the Coordinated Data Analysis Workshops Data Center, which contains all CMEs manually identified since 1996 using the Large Angle and Spectrometric Coronagraph (LASCO) on board the Solar and Heliospheric Observatory. We use LASCO C2 data in the period between 1996 January and 2020 December to train, validate, and test DeepCME through 10-fold cross validation. The DeepCME method is a fusion of three deep-learning models, namely ResNet, InceptionNet, and InceptionResNet. Our fusion model extracts features from LASCO C2 images, effectively combining the learning capabilities of the three component models to jointly estimate the mass and kinetic energy of CMEs. Experimental results show that the fusion model yields a mean relative error (MRE) of 0.013 (0.009, respectively) compared to the MRE of 0.019 (0.017, respectively) of the best component model InceptionResNet (InceptionNet, respectively) in estimating the CME mass (kinetic energy, respectively). To our knowledge, this is the first time that deep learning has been used for CME mass and kinetic energy estimations.https://doi.org/10.3847/2041-8213/ad0c4aSolar atmosphereSolar coronal mass ejectionsConvolutional neural networks |
| spellingShingle | Khalid A. Alobaid Yasser Abduallah Jason T. L. Wang Haimin Wang Shen Fan Jialiang Li Huseyin Cavus Vasyl Yurchyshyn Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models The Astrophysical Journal Letters Solar atmosphere Solar coronal mass ejections Convolutional neural networks |
| title | Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models |
| title_full | Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models |
| title_fullStr | Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models |
| title_full_unstemmed | Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models |
| title_short | Estimating Coronal Mass Ejection Mass and Kinetic Energy by Fusion of Multiple Deep-learning Models |
| title_sort | estimating coronal mass ejection mass and kinetic energy by fusion of multiple deep learning models |
| topic | Solar atmosphere Solar coronal mass ejections Convolutional neural networks |
| url | https://doi.org/10.3847/2041-8213/ad0c4a |
| work_keys_str_mv | AT khalidaalobaid estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT yasserabduallah estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT jasontlwang estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT haiminwang estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT shenfan estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT jialiangli estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT huseyincavus estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels AT vasylyurchyshyn estimatingcoronalmassejectionmassandkineticenergybyfusionofmultipledeeplearningmodels |