A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample
文献类型：期刊论文
| 作者 | Ma,Zhixian1; Xu,Haiguang2,3,7; Zhu,Jie1; Hu,Dan3; Li,Weitian3; Shan,Chenxi3; Zhu,Zhenghao3; Gu,Liyi4; Li,Jinjin5; Liu,Chengze3 |
| 刊名 | The Astrophysical Journal Supplement Series
 |
| 出版日期 | 2019-02-12 |
| 卷号 | 240期号:2 |
| 关键词 | catalogs galaxies: statistics methods: data analysis radio continuum: galaxies techniques: miscellaneous |
| ISSN号 | 0067-0049 |
| DOI | 10.3847/1538-4365/aaf9a2 |
| 英文摘要 | Abstract We present a morphological classification of 14,245 radio active galactic nuclei (AGNs) into six types, i.e., typical Fanaroff–Riley Class I/II (FRI/II), FRI/II-like bent-tailed, X-shaped radio galaxy, and ringlike radio galaxy, by designing a convolutional neural network based autoencoder, namely MCRGNet, and applying it to a labeled radio galaxy (LRG) sample containing 1442 AGNs and an unlabeled radio galaxy (unLRG) sample containing 14,245 unlabeled AGNs selected from the Best–Heckman sample. We train MCRGNet and implement the classification task by a three-step strategy, i.e., pre-training, fine-tuning, and classification, which combines both unsupervised and supervised learnings. A four-layer dichotomous tree is designed to classify the radio AGNs, which leads to a significantly better performance than the direct six-type classification. On the LRG sample, our MCRGNet achieves a total precision of ～93% and an averaged sensitivity of ～87%, which are better than those obtained in previous works. On the unLRG sample, whose labels have been human-inspected, the neural network achieves a total precision of ～80%. Also, using Sloan Digital Sky Survey Data Release 7 to calculate the r-band absolute magnitude (Mopt) and using the flux densities to calculate the radio luminosity (Lradio), we find that the distributions of the unLRG sources on the Lradio–Mopt plane do not show an apparent redshift evolution and could confirm with a sufficiently large sample that there could not exist an abrupt separation between FRIs and FRIIs as reported in some previous works. |
| 语种 | 英语 |
| WOS记录号 | IOP:0067-0049-240-2-AAF9A2 |
| 出版者 | The American Astronomical Society |
| 源URL | [http://ir.bao.ac.cn/handle/114a11/35481]  |
| 专题 | 中国科学院国家天文台 |
| 作者单位 | 1.Department of Electronic Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang, Shanghai 200240, People’s Republic of China mazhixian@sjtu.edu.cn, zhujie@sjtu.edu.cn 2.IFSA Collaborative Innovation Center, Shanghai Jiao Tong University, Minhang, Shanghai 200240, People’s Republic of China 3.Department of Astronomy, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang, Shanghai 200240, People’s Republic of China 4.SRON Netherlands Institute for Space Research, Sorbonnelaan 2, 3584 CA Utrecht, The Netherlands 5.Key Laboratory of Thin Film and Microfabrication Technology (Ministry of Education), Department of Micro/Nano Electronics, Shanghai Jiao Tong University, Shanghai 200240, People’s Republic of China 6.National Astronomical Observatories, Chinese Academy of Sciences, 20A Datun Road, Beijing 100012, People’s Republic of China 7.School of Physics and Astronomy/Tsung-Dao Lee Institute, Shanghai Jiao Tong University, 800 Dongchuan Road, Minhang, Shanghai 200240, People’s Republic of China; hgxu@sjtu.edu.cn |
| 推荐引用方式 GB/T 7714 | Ma,Zhixian,Xu,Haiguang,Zhu,Jie,et al. A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample[J]. The Astrophysical Journal Supplement Series,2019,240(2). |
| APA | Ma,Zhixian.,Xu,Haiguang.,Zhu,Jie.,Hu,Dan.,Li,Weitian.,...&Wu,Xiangping.(2019).A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample.The Astrophysical Journal Supplement Series,240(2). |
| MLA | Ma,Zhixian,et al."A Machine Learning Based Morphological Classification of 14,245 Radio AGNs Selected from the Best–Heckman Sample".The Astrophysical Journal Supplement Series 240.2(2019). |
入库方式： OAI收割
来源：国家天文台
浏览0
下载0
收藏0
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。