Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks
Abstract The spatial distribution of aurora intensity is an important manifestation of solar wind‐magnetosphere‐ionosphere energy coupling process, and it oscillates with the change of space environment parameters and geomagnetic index. It is of great significance to establish an appropriate aurora...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-11-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2021SW002751 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536478757257216 |
|---|---|
| author | Ze‐Jun Hu Bing Han Yisheng Zhang Huifang Lian Ping Wang Guojun Li Bin Li Xiang‐Cai Chen Jian‐Jun Liu |
| author_facet | Ze‐Jun Hu Bing Han Yisheng Zhang Huifang Lian Ping Wang Guojun Li Bin Li Xiang‐Cai Chen Jian‐Jun Liu |
| author_sort | Ze‐Jun Hu |
| collection | DOAJ |
| description | Abstract The spatial distribution of aurora intensity is an important manifestation of solar wind‐magnetosphere‐ionosphere energy coupling process, and it oscillates with the change of space environment parameters and geomagnetic index. It is of great significance to establish an appropriate aurora intensity model for the prediction of space weather and the study of magnetosphere dynamics. Based on Ultraviolet Imager (UVI) data of Polar satellite, we constructed two auroral models by using two different neural networks, that is, the generalized regression neural network (GRNN), and the conditional generation adversarial network (CGAN). Input parameters of the models include interplanetary magnetic field, solar wind velocity and density, and the geomagnetic AE index. Output result is the spatial distribution of auroral intensity in altitude adjusted corrected geomagnetic (AACGM) coordinates. The structural similarity index (SSIM) of image quality is used as an evaluation standard of detail similarity between the prediction results of auroral intensity model and corresponding UVI images (complete similarity is 1, dissimilarity is 0, SSIM is generally considered to have good similarity if it is greater than 0.5). Based on the respective training datasets of GRNN and CGAN models, the evaluating results showed that the mean values (standard deviation) of SSIM were 0.5409 (0.0912) and 0.5876 (0.0712), respectively, so the prediction results from both models can restore the auroral intensity distribution of the original images of UVI. In addition, the value of SSIM can increase with the increase of the number of training data. Therefore, more training data will help improve the effectiveness of these models. |
| format | Article |
| id | doaj-art-470c1db93d80489d824090e31dd20086 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2021-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-470c1db93d80489d824090e31dd200862025-01-14T16:27:04ZengWileySpace Weather1542-73902021-11-011911n/an/a10.1029/2021SW002751Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural NetworksZe‐Jun Hu0Bing Han1Yisheng Zhang2Huifang Lian3Ping Wang4Guojun Li5Bin Li6Xiang‐Cai Chen7Jian‐Jun Liu8MNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaSchool of Electronic Engineering Xidian University Xi'an ChinaInstitute of Applied Meteorology Beijing ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaMNR Key Laboratory for Polar Science Polar Research Institute of China Shanghai ChinaAbstract The spatial distribution of aurora intensity is an important manifestation of solar wind‐magnetosphere‐ionosphere energy coupling process, and it oscillates with the change of space environment parameters and geomagnetic index. It is of great significance to establish an appropriate aurora intensity model for the prediction of space weather and the study of magnetosphere dynamics. Based on Ultraviolet Imager (UVI) data of Polar satellite, we constructed two auroral models by using two different neural networks, that is, the generalized regression neural network (GRNN), and the conditional generation adversarial network (CGAN). Input parameters of the models include interplanetary magnetic field, solar wind velocity and density, and the geomagnetic AE index. Output result is the spatial distribution of auroral intensity in altitude adjusted corrected geomagnetic (AACGM) coordinates. The structural similarity index (SSIM) of image quality is used as an evaluation standard of detail similarity between the prediction results of auroral intensity model and corresponding UVI images (complete similarity is 1, dissimilarity is 0, SSIM is generally considered to have good similarity if it is greater than 0.5). Based on the respective training datasets of GRNN and CGAN models, the evaluating results showed that the mean values (standard deviation) of SSIM were 0.5409 (0.0912) and 0.5876 (0.0712), respectively, so the prediction results from both models can restore the auroral intensity distribution of the original images of UVI. In addition, the value of SSIM can increase with the increase of the number of training data. Therefore, more training data will help improve the effectiveness of these models.https://doi.org/10.1029/2021SW002751ultraviolet auroral intensity modelneural networksinterplanetary and geomagnetic parametersgeneralized regression neural networkconditional generation adversarial network |
| spellingShingle | Ze‐Jun Hu Bing Han Yisheng Zhang Huifang Lian Ping Wang Guojun Li Bin Li Xiang‐Cai Chen Jian‐Jun Liu Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks Space Weather ultraviolet auroral intensity model neural networks interplanetary and geomagnetic parameters generalized regression neural network conditional generation adversarial network |
| title | Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks |
| title_full | Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks |
| title_fullStr | Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks |
| title_full_unstemmed | Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks |
| title_short | Modeling of Ultraviolet Aurora Intensity Associated With Interplanetary and Geomagnetic Parameters Based on Neural Networks |
| title_sort | modeling of ultraviolet aurora intensity associated with interplanetary and geomagnetic parameters based on neural networks |
| topic | ultraviolet auroral intensity model neural networks interplanetary and geomagnetic parameters generalized regression neural network conditional generation adversarial network |
| url | https://doi.org/10.1029/2021SW002751 |
| work_keys_str_mv | AT zejunhu modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT binghan modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT yishengzhang modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT huifanglian modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT pingwang modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT guojunli modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT binli modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT xiangcaichen modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks AT jianjunliu modelingofultravioletauroraintensityassociatedwithinterplanetaryandgeomagneticparametersbasedonneuralnetworks |