3种聚类算法在疏散星团成员星证认中的性能对比  

Performance Comparison of Three Clustering Algorithms in Open Cluster Member Star Identification

作　　者：熊壮 张鹏 杨向明[1] 刘高潮 刘迪[1] 李佳朋 田海俊 XIONG Zhuang;ZHANG Peng;YANG Xiang-ming;LIU Gao-chao;LIU Di;LI Jia-peng;TIAN Hai-jun(College of Science,China Three Gorges University,Yichang 443002;Center for Astronomy and Space Sciences,China Three Gorges University,Yichang 443002;College of Science,Hangzhou Dianzi University,Hangzhou 310018)

机构地区：[1]三峡大学理学院,宜昌443002 [2]三峡大学天文与空间科学研究中心,宜昌443002 [3]杭州电子科技大学理学院,杭州310018

出　　处：《天文学报》2025年第2期62-75,共14页Acta Astronomica Sinica

基　　金：国家自然科学基金项目(12373033、12373030);湖北省自然科学基金项目(2023AFB577)资助。

摘　　要：长期以来,疏散星团成员星的证认问题一直是天文学领域的一个挑战,由于疏散星团形成及演化的复杂性,没有统一的方法能准确地确定疏散星团中的成员星.目标是以3种不同空间分布类型的疏散星团为样本,选取恒星的位置和运动的五维参数,通过DBSCAN(Density-Based Spatial Clustering of Applications with Noise)、FOF(Friend of Friend)和STAR GO(Star's Galactic Origin)3种聚类方法,对疏散星团进行聚类检测,量化不同算法的绩效.研究结果表明,FOF与STAR GO算法对有特殊结构的星团更为适用,能识别出星团的潮汐或延展结构,而DBSCAN对星团核心区域成员星的识别更为完整.旨在星团结构细节与提高成员星识别的完整性之间找到更均衡的算法策略.For a long time,the identification of open cluster member stars has been a challenge in the field of astronomy.Due to the complexity of the formation and evolution of open cluster,there is no unified method to accurately identify the member stars in open cluster.The objective is to select five dimensional parameters of the position and motion of stars from three different spatial distribution types of open star clusters.This study evaluates the performance of Density Based Spatial Clustering of Applications with Noise(DBSCAN),Friend-of-Friend(FOF)and Star’s Galactic Origin(STAR GO)clustering methods in detecting open star clusters.The results show that the FOF and STAR GO algorithms are more suitable for clusters with special structure,and can identify the tidal or extended structure of the cluster,while DBSCAN can identify the member stars in the core region of the cluster more completely.The aim is to find a more balanced algorithm strategy between the details of the cluster structure and the integrity of the member star recognition.

关 键 词：疏散星团和星团:个别:Trumpler 10 NGC 752 NGC 2232 Tian 2 方法:数据分析 天文数据库:盖亚卫星数据 

分 类 号：P154[天文地球—天文学]