Morphological Classification of Galaxies Through Structural and Star Formation Parameters Using Machine Learning
G. Aguilar-Argüello, G. Fuentes-Pineda, H. M. Hernández-Toledo, L. A. Martínez-Vázquez, J. A. Vázquez-Mata, S. Brough, R. Demarco, A. Ghosh, Y. Jiménez-Teja, G.… 展开作者
G. Aguilar-Argüello, G. Fuentes-Pineda, H. M. Hernández-Toledo, L. A. Martínez-Vázquez, J. A. Vázquez-Mata, S. Brough, R. Demarco, A. Ghosh, Y. Jiménez-Teja, G. Martin, W. J. Pearson, C. Sifón
We employ the XGBoost machine learning (ML) method for the morphological classification of galaxies into two (early-type, late-type) and five (E, S0--S0a, Sa--Sb, Sbc--Scd, Sd--Irr) classes, using a combination of non-parametric ($C,\,A,\,S,\,A_S,\,\mathrm{Gini},\,M_{20},\,c_{5090}$), parametric (Sérsic index, $n$), geometric (axial ratio, $BA$), global colour ($g-i,\,u-r,\,u-i$), colour gradient ($Δ(g - i)$), and asymmetry gradient ($ΔA_{9050}$) information, all estimated for a local galaxy sample ($z<0.15$) compiled from the Sloan Digital Sky Survey (SDSS) imaging data. We train the XGBoost model and evaluate its performance through multiple standard metrics. Our findings reveal better performance when utilizing all fourteen parameters, achieving accuracies of 88\% and 65\% for the two-class and five-class classification tasks, respectively. In addition, we investigate a hierarchical classification approach for the five-class scenario, combining three XGBoost classifiers. We observe comparable performance to the ``direct'' five-class classification, with discrepancies of only up to 3\%. Using SHAP (an advanced interpretation tool), we analyse how galaxy parameters impact the model's classifications, providing valuable insights into the influence of these features on classification outcomes. Finally, we compare our results with previous studies and find them consistently aligned.
Machine learning technique for morphological classification of galaxies from SDSS. II. The image-based morphological catalogs of galaxies at 0.02<z<0.1
Machine learning technique for morphological classification of galaxies from the SDSS. I. Photometry-based approach
方法.我们使用了不同的星系分类技术:人类标记,多光度图,朴素贝叶斯,逻辑回归,支持向量机,随机森林,k最近邻和k倍验证。结果我们提出了一个二进制自动形态分类的星系进行人类标记,multiphotometrics,监督机器学习方法的结果。我们将其应用于SDSS DR 9中0.02 < z < 0.1和24 m < Mr <19.4 m的星系样本。为了研究分类器,我们使用绝对量值:Mu、Mg、Mr、Mi、Mz、Mu-Mr、Mg-Mi、Mu-Mg、Mr-Mz,以及中心R50/R90的逆浓度指数。使用支持向量机分类器和数据的颜色指数,绝对星等,与视觉形态类型的星系的逆浓度指数,我们能够分类316 031个星系从SDSS DR 9与未知的形态类型。结论. Python中的Scikit-learn机器学习支持向量机和随机森林方法为二元星系形态分类提供了最高的准确率:分别为96.4%的正确分类(96.1%早期E型和96.9%晚期L型)和95.5%的正确分类(96.7%早期E型和92.8%晚期L型)。对SDSS DR 9中z < 0.1的316031个星系样本进行支持向量机分类,得到141211 E型和174820 L型星系。
Molecular Gas Morphological Analogues for the Milky Way
The University of Texas at Austin(德克萨斯大学奥斯汀分校);INAF-IAPS(意大利国家天体物理研究所国际天体物理中心);INAF, Sezione di Lecce(意大利国家天体物理研究所莱切分部);National Astronomical Observatory of Japan(日本国立天文台);Max Planck Institute for Radio Astronomy(马克斯·普朗克射电天文研究所);University of Kentucky(肯塔基大学)
Satellite quenching and morphological transformation of galaxies in groups and clusters
Department of Physics and Astronomy, McMaster University(麦克马斯特大学物理与天文学系);NAT-Universidade Cidade de São Paulo(圣保罗城市大学);School of Physics and Astronomy, University of Nottingham(诺丁汉大学物理与天文学院)
Machine learning technique for morphological classification of galaxies from SDSS. IV. CNN-Assisted Expert Validation of Morphological Catalogues for Merging, Irregular, Edge-on, Barred, Ringed, and Dust-lane Galaxies at 0.003 < z < 0.1
Main Astronomical Observatory of the NAS of Ukraine(乌克兰国家科学院主天文台)
The GMRT archive atomic gas survey -- IV. Consistency of the dark matter halo perturbation parameter from morphological and kinematic lopsidedness of galaxies
Indian Institute of Astrophysics(印度天体物理研究所);Department of Astronomy, Astrophysics and Space Engineering, Indian Institute of Technology Indore(印多尔理工学院天文、天体物理与空间工程系);Max Planck Institute for Radioastronomy(马克斯·普朗克射电天文研究所);Institute of Astronomy and National Astronomical Observatory, Bulgarian Academy of Sciences(保加利亚科学院天文与国家天文台)
The morphological evolution, AGN fractions, dust content, environments, and downsizing of massive green valley galaxies at 0.5<z<2.5 in 3D-HST/CANDELS
为了探讨红、绿、蓝星系群之间的演化联系,我们以5个3D-HST/CANDELS场中0.5<z<2.5的大质量($M_* > 10^{10} M_{\odot} $)星系为样本,研究了这3个星系群的尘埃含量、形态、结构、活动星系核分数和环境。绿谷星系被发现有中等的尘埃衰减,并居住在中间的区域所占据的静止和恒星形成星系的UVJ图。与z<2的蓝色和红色星系相比,绿色星系具有中等的紧凑性和形态参数,如Sersic指数,浓度,Gini系数和星系20%最亮像素的二阶矩。上述发现似乎支持了这样一种假设,即当恒星形成星系被淬灭进入静止状态时,绿色星系正处于过渡阶段。z<2的绿色星系显示出最高的活动星系核分数,这表明活动星系核反馈可能在恒星形成猝灭中发挥了重要作用。对于2<z<2.5的大质量星系,红星系和绿星系的活动星系核分数都比蓝星系高,这意味着活动星系核反馈可能有助于保持z>2的红星系的静止。在z = 0.5时,绿星系和红星系的<1.5. Green and blue galaxies at z>局域密度分布相似,表明在z>0.5时,环境猝灭不是停止恒星形成的主要机制。作为质量的函数的三个人口的分数支持一个“缩小”淬火图片,大部分的恒星形成在更大质量的星系比低质量的星系早完成。
The Next Generation Virgo Cluster Survey (NGVS). XL. The Morphological Classification of Virgo Cluster Galaxies
University of Victoria(维多利亚大学);Peking University(北京大学);Kavli Institute for Astronomy and Astrophysics, Peking University(北京大学科维理天文与天体物理研究所);NSF’s NOIRLab(美国国家科学基金会NOIR实验室);Shanghai Jiao Tong University(上海交通大学);Kangwon National University(江原国立大学);UK Astronomy Technology Centre, Royal Observatory(英国天文学技术中心皇家天文台);University of the Pacific(太平洋大学);University of California Santa Cruz(加州大学圣克鲁兹分校);Youngstown State University(扬斯敦州立大学);Université de Strasbourg(斯特拉斯堡大学);Case Western Reserve University(凯斯西储大学);University of Calgary(卡尔加里大学);University of Manitoba(曼尼托巴大学);Princeton University(普林斯顿大学)
Modeling the effects of dust evolution on the SEDs of galaxies of different morphological type
我们提出的光度演化模型的星系,其中,除了恒星的组成部分,不断变化的尘埃星际介质的影响已被列入特别照顾。从Calura、Pipino和Matteucci(2008年)的工作开始,其中化学演化模型已被用于研究太阳邻域、椭圆星系和不规则星系中星际介质的气体和尘埃成分的演化,将这些模型与包括尘埃再处理(GRASIL)在内的分光光度恒星代码相结合是可能的(Silva et al. 1998)来分析这些星系的光谱能量分布(SED)的演化。我们测试我们的模型对所观察到的SED在本地宇宙和高红移,并使用它们来预测如何再处理的星光的百分比演变为每种类型的星系。通过比较我们的结果与通过采用简单的假设来处理这个组件所获得的结果,研究了以下尘埃演变的重要性。
Morphological and Star Formation Properties of Cosmic Noon Massive Quiescent Galaxies
Indian Institute of Science Education and Research Pune(印度科学教育研究所浦那分校);National Centre for Radio Astrophysics – Tata Institute of Fundamental Research(国家射电天体物理中心 - 塔塔基础研究院)
Visual morphological classification of the full MaNGA DR17 sample: a general characterization
Universidad Nacional Autónoma de México. Instituto de Astronomía(墨西哥国立自治大学天文学研究所);Instituto de Astronomía y Ciencias Planetarias, Universidad de Atacama(阿塔卡马大学天文与行星科学研究所);Departamento de Física, Facultad de Ciencias, Universidad Nacional Autónoma de México(墨西哥国立自治大学理学院物理系)
A robust morphological classification method for galaxies using dual-encoding contrastive learning and multi-clustering voting on JWST/NIRCam images
School of Mathematics and Physics, Anqing Normal University(安庆师范大学数学与物理学院);Institute of Astronomy and Astrophysics, Anqing Normal University(安庆师范大学天文与天体物理研究所);Key Laboratory of Modern Astronomy and Astrophysics (Nanjing University), Ministry of Education(教育部现代天文与天体物理重点实验室(南京大学));Department of Physics, The Chinese University of Hong Kong(香港中文大学物理系);Shanghai Astronomical Observatory, Chinese Academy of Sciences(中国科学院上海天文台);School of Astronomy and Space Science, University of Chinese Academy of Sciences(中国科学院大学天文与空间科学学院);School of Engineering, Dali University(大理大学工程学院)
Galaxies Below the Fundamental Metallicity Relation Are Morphologically Disturbed: Merian H$α$ Morphologies and DESI Metallicities
Princeton University(普林斯顿大学);Tel Aviv University(特拉维夫大学);Stanford University(斯坦福大学);University of California, Santa Cruz(加州大学圣克鲁兹分校);Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室);The Ohio State University(俄亥俄州立大学);Amherst College(阿默斯特学院)