Using deep Residual Networks to search for galaxy-Ly alpha emitter lens candidates based on spectroscopic selection
文献类型：期刊论文
| 作者 | Li, Rui1,2,3,4; Shu, Yiping5,6; Su, Jianlin7; Feng, Haicheng1,2,3,4; Zhang, Guobao1,2,3,4; Wang, Jiancheng1,2,3,4; Liu, Hongtao1,2,3,4 |
| 刊名 | MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
 |
| 出版日期 | 2019 |
| 卷号 | 482期号:1页码:313-320 |
| ISSN号 | 0035-8711 |
| 关键词 | gravitational lensing: strong galaxies: structure |
| DOI | 10.1093/mnras/sty2708 |
| 通讯作者 | Li, Rui(lirui@ynao.ac.cn) |
| 英文摘要 | More than 100 galaxy-scale strong gravitational lens systems have been found by searching for the emission lines coming from galaxies with redshifts higher than the lens galaxies. Based on this spectroscopic-selection method, we introduce the deep Residual Networks (ResNet; a kind of deep Convolutional Neural Networks) to search for the galaxy-Ly alpha emitter (LAE) lens candidates by recognizing the Ly alpha emission lines coming from high- redshift galaxies (2 < z < 3) in the spectra of early-type galaxies (ETGs) at middle redshift (z similar to 0.5). The spectra of the ETGs come from the Data Release 12 (DR12) of the Baryon Oscillation Spectroscopic Survey (BOSS) of the Sloan Digital Sky Survey III (SDSS-III). In this paper, we first build a 28 layers ResNet model, and then artificially synthesize 150 000 training spectra, including 140 000 spectra without Ly alpha lines and 10 000 ones with Ly alpha lines, to train the networks. After 20 training epochs, we obtain a near-perfect test accuracy at 0.995 4. The corresponding loss is 0.002 8 and the completeness is 93.6 per cent. We finally apply our ResNet model to our predictive data with 174 known lens candidates. We obtain 1232 hits including 161 of the 174 known candidates (92.5 per cent discovery rate). Apart from the hits found in other works, our ResNet model also find 536 new hits. We then perform several subsequent selections on these 536 hits and present five most believable lens candidates. |
| WOS关键词 | ACS SURVEY ; AUTOMATIC DETECTION ; STELLAR ; SAMPLE |
| WOS研究方向 | Astronomy & Astrophysics |
| 语种 | 英语 |
| 出版者 | OXFORD UNIV PRESS |
| WOS记录号 | WOS:000454575300024 |
| 源URL | [http://libir.pmo.ac.cn/handle/332002/20505]  |
| 专题 | 中国科学院紫金山天文台 |
| 通讯作者 | Li, Rui |
| 作者单位 | 1.Chinese Acad Sci, Yunnan Observ, 396 Yangfangwang, Kunming 650216, Yunnan, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China 3.Chinese Acad Sci, Ctr Astron Mega Sci, 20A Datun Rd, Beijing 100012, Peoples R China 4.Chinese Acad Sci, Key Lab Struct & Evolut Celestial Objects, 396 Yangfangwang, Kunming 650216, Yunnan, Peoples R China 5.Chinese Acad Sci, Purple Mt Observ, 2 West Beijing Rd, Nanjing 210008, Jiangsu, Peoples R China 6.Univ Cambridge, Inst Astron, Madingley Rd, Cambridge CB3 0HA, England 7.Sun Yat Sen Univ, Sch Math, Guangzhou, Guangdong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Rui,Shu, Yiping,Su, Jianlin,et al. Using deep Residual Networks to search for galaxy-Ly alpha emitter lens candidates based on spectroscopic selection[J]. MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,2019,482(1):313-320. |
| APA | Li, Rui.,Shu, Yiping.,Su, Jianlin.,Feng, Haicheng.,Zhang, Guobao.,...&Liu, Hongtao.(2019).Using deep Residual Networks to search for galaxy-Ly alpha emitter lens candidates based on spectroscopic selection.MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY,482(1),313-320. |
| MLA | Li, Rui,et al."Using deep Residual Networks to search for galaxy-Ly alpha emitter lens candidates based on spectroscopic selection".MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY 482.1(2019):313-320. |
入库方式： OAI收割
来源：紫金山天文台
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。