人工智能在脉冲星候选体筛选中的应用  

Application of Artificial Intelligence in the Selection of Pulsar Candidate

作　　者：许余云 李菂 刘志杰[1] 王晨 王培[2] 张蕾[2] 潘之辰 XU Yu-yun;LI Di;LIU Zhi-jie;WANG Chen;WANG Pei;ZHANG lei;PAN Zhi-chen(Guizhou Normal University, Key Laboratory of Information and Computing Science Guizhou Province,Guizhou 550001, China;National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, China;Key Laboratory of Radio Astronomy, Chinese Academy of Sciences, Nanjing 2100008,China;Commonwealth Scienti c and Industrial Research Organisation, Canberra ACT 2601, Australia)

机构地区：[1]贵州师范大学贵州省信息与计算科学重点实验室,贵阳550001 [2]中国科学院国家天文台,北京100012 [3]中国科学院射电天文实验室,南京210008 [4]澳大利亚联邦科学与工业研究组织

出　　处：《天文学进展》2017年第3期304-315,共12页Progress In Astronomy

基　　金：研究生创新基金项目(研创201528);国家自然科学基金(U1631132);中国科学院国际合作局对外合作重点项目(114A11KYSB20160008);中国科学院战略性先导科技专项(B类)(XDB23000000)

摘　　要：脉冲星搜寻是对脉冲星、引力波,以及对快速射电暴(Fast Radio Burst,简称FRB)等暂现源进行研究的基础。搜寻不仅可以扩大脉冲星样本,还可以发现极端性质的致密星。这有助于研究致密天体状态方程、星际介质、脉冲星导航、引力波探测等课题。目前,射电望远镜的单次巡天就可以产生百万数量级的脉冲星候选体。面对这些海量数据,仅仅依赖人工识别筛选,已不能满足数据的时效需求,更不能实现数据的实时处理。机器学习、计算机视觉应用等人工智能技术自诞生以来,其理论和技术已日益发展成熟,并已成功运用到脉冲星候选体筛选等射电天文研究领域。首先将介绍现有脉冲星搜寻的人工智能方法,再统计和分析已有脉冲星候选体筛选方法的性能,最后对FAST脉冲星候选体筛选工作进行展望。Pulsar searching,aiming at discovering pulsars and transient sources such as Rotation RAdio Transients and Fast Radio Bursts(FRB),is the first step of sciences based on pulsars and transient sources.As more pulsars are discovered in pulsar searches,some special kinds of pulsars,including those having very short spin periods and very eccentric orbits,will also be illuminated.These special pulsars provide extreme physical conditions for us to examine our current understands,which is imperative to the research of the dense matter state equation,interplanetary navigation,the interstellar medium,and the measurement of gravitational waves.

关 键 词：人工智能 脉冲星 候选体筛选 

分 类 号：P162.4[天文地球—天文学]