版权说明 操作指南
首页 > 成果 > 详情

Deep Learning for Identification and Characterization of Ca ii Absorption Lines: A Multitask Convolutional Neural Network Approach

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Liu, Yang;Li, Jie;Gao, Linqing;Zhang, Haotong;Xu, Zhenghua;...
通讯作者:
Xu, ZH
作者机构:
[Lin, Wenbin; Liu, Yang] Univ South China, Sch Comp Sci, Hengyang 421001, Peoples R China.
[Lin, Wenbin; Xu, Zhenghua; Li, Jie; Gao, Linqing] Univ South China, Sch Math & Phys, Hengyang 421001, Peoples R China.
[Zhang, Haotong] Chinese Acad Sci, Natl Astron Observ, Beijing 100101, Peoples R China.
[Wang, Yu] Sapienza Univ Roma, ICRA & Dipartimento Fis, Piazzale Aldo Moro 5, I-00185 Rome, Italy.
[Lin, Wenbin; Wang, Yu] ICRANet, Pzza Repubbl 10, I-65122 Pescara, Italy.
通讯机构:
[Xu, ZH ] U
Univ South China, Sch Math & Phys, Hengyang 421001, Peoples R China.
语种:
英文
期刊:
ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES
ISSN:
0067-0049
年:
2025
卷:
276
期:
2
页码:
37
基金类别:
MOST divided by National Natural Science Foundation of China (NSFC)https://doi.org/10.13039/501100001809 [11973025]; National Natural Science Foundation of China
机构署名:
本校为第一且通讯机构
院系归属:
数理学院
摘要:
Quasar absorption lines are a powerful tool for studying the Universe, enabling us to probe distant gas, dust, and galaxy formation and evolution. However, detecting these lines, particularly Ca ii absorption lines, is a time-consuming and laborious process. Existing deep learning methods are prone to false positives and still require extensive manual verification and parameter measurement. This work presents three multitask convolutional neural network models and identifies the ResNet-CBAM model, which incorporates residual learning and an attention mechanism as the most effective. The result...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com