Automatic classification of mesoscale auroral forms using convolutional neural networks
文献类型:期刊论文
作者 | Guo, Z.-X.6,7; Yang, J.-Y.5,6,7; Dunlop, M. W.4,6,7; Cao, J.-B.6,7; Li, L.-Y.6,7; Ma, Y.-D.6,7; Ji KF(季凯帆)3; Xiong, C.2; Li, J.6,7; Ding, W.-T.1 |
刊名 | Journal of Atmospheric and Solar-Terrestrial Physics |
出版日期 | 2022-09-01 |
卷号 | 235 |
ISSN号 | 1364-6826 |
DOI | 10.1016/j.jastp.2022.105906 |
产权排序 | 第5完成单位 |
文献子类 | Journal article (JA) |
英文摘要 | Convolutional neural networks (CNNs) in deep learning enable the extraction of features in image data. Through the multi-layer superposition of a convolutional neural network, we can better capture the essential characteristics of different auroral subclasses and further classify auroral images in detail. Because the auroral morphological features often present abstract characteristics, our study compares different CNN architectures and different layering in order to test the best neural network model for mesoscale aurora classification. Although the classification models and subclasses used by us are both more complex, the highest F1 score of aurora classification of the test set reaches 99.6% (ResNet-50), which performs best comparing with previous works. Our classification models work also quite well when applied to an independent auroral image sequence, declaring our approach can automatically select images of various mesoscale auroral forms using CNNs, and allow the time sequence of auroral evolution to be seen automatically through the mesoscale auroral feature recognitions. |
学科主题 | 计算机科学技术 ; 人工智能 ; 计算机应用 |
URL标识 | 查看原文 |
资助项目 | National Natural Science Foundation of China[41431071] ; National Natural Science Foundation of China[41821003] ; National Natural Science Foundation of China[4187419] |
语种 | 英语 |
出版者 | Elsevier Ltd |
资助机构 | National Natural Science Foundation of China[41431071,41821003,4187419] |
源URL | [http://ir.ynao.ac.cn/handle/114a53/25212] |
专题 | 天文技术实验室 |
作者单位 | 1.Sinosteel Tendering Co., LTD, No. 8, Haidian Street, Haidian District, Beijing, China 2.Department of Space Physics, Electronic Information School, Wuhan University, Wuhan, 430072, China; 3.Yunnan Observatory of Chinese Academy of Science, Yunnan, 650216, China; 4.RAL_Space, STFC, Chilton, Oxfordshire, OX11 0QX, United Kingdom; 5.State Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences, Beijing, China; 6.Key Laboratory of Space Environment Monitoring and Information Processing, Ministry of Industry and Information Technology, China; 7.Space Science Institute, School of Space and Environment, Beihang University, Beijing, 100191, China; |
推荐引用方式 GB/T 7714 | Guo, Z.-X.,Yang, J.-Y.,Dunlop, M. W.,et al. Automatic classification of mesoscale auroral forms using convolutional neural networks[J]. Journal of Atmospheric and Solar-Terrestrial Physics,2022,235. |
APA | Guo, Z.-X..,Yang, J.-Y..,Dunlop, M. W..,Cao, J.-B..,Li, L.-Y..,...&Ding, W.-T..(2022).Automatic classification of mesoscale auroral forms using convolutional neural networks.Journal of Atmospheric and Solar-Terrestrial Physics,235. |
MLA | Guo, Z.-X.,et al."Automatic classification of mesoscale auroral forms using convolutional neural networks".Journal of Atmospheric and Solar-Terrestrial Physics 235(2022). |
入库方式: OAI收割
来源:云南天文台
其他版本
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。