Detecting HI Galaxies with Deep Neural Networks in the Presence of Radio Frequency Interference

作     者：Ruxi Liang Furen Deng Zepei Yang Chunming Li Feiyu Zhao Botao Yang Shuanghao Shu Wenxiu Yang Shifan Zuo Yichao Li Yougang Wang Xuelei Chen Ruxi Liang;Furen Deng;Zepei Yang;Chunming Li;Feiyu Zhao;Botao Yang;Shuanghao Shu;Wenxiu Yang;Shifan Zuo;Yichao Li;Yougang Wang;Xuelei Chen

作者机构：National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China University of Chinese Academy of SciencesBeijing 101408China Department of PhysicsNortheastern UniversityBostonMA 02115USA Biomedical Instrument InstituteSchool of Biomedical EngineeringShanghai Jiao Tong UniversityShanghai 200030China Shanghai Astronomical ObservatoryChinese Academy of SciencesShanghai 200030China Key Laboratory of Cosmology and Astrophysics(Liaoning)College of SciencesNortheastern UniversityShenyang 110819China Key Laboratory of Radio Astronomy and TechnologyChinese Academy of SciencesBeijing 100101China 

出 版 物：《Research in Astronomy and Astrophysics》 (天文和天体物理学研究（英文版）)

年 卷 期：2023年第23卷第11期

页      面：38-50页

核心收录：

学科分类：07[理学] 070401[理学-天体物理] 0704[理学-天文学] 

基　　金：support by the National SKA Program of China No.2022SKA0110100 the CAS Interdisciplinary Innovation Team(JCTD-2019-05) the science research grants from the China Manned Space Project with No.CMS-CSST-2021-B01 

主　　题：methods:data analysis methods:observational techniques:image processing 

摘      要：In the neutral hydrogen(H I)galaxy survey,a significant challenge is to identify and extract the H I galaxy signal from the observational data contaminated by radio frequency interference(RFI).For a drift-scan survey,or more generally a survey of a spatially continuous region,in the time-ordered spectral data,the H I galaxies and RFI all appear as regions that extend an area in the time-frequency waterfall plot,so the extraction of the H I galaxies and RFI from such data can be regarded as an image segmentation problem,and machine-learning methods can be applied to solve such *** this study,we develop a method to effectively detect and extract signals of H I galaxies based on a Mask R-CNN network combined with the PointRend *** simulating FAST-observed galaxy signals and potential RFI impact,we created a realistic data set for the training and testing of our neural *** compared five different architectures and selected the best-performing *** architecture successfully performs instance segmentation of H I galaxy signals in the RFI-contaminated time-ordered data,achieving a precision of 98.64%and a recall of 93.59%.