Artificial neural networks (ANN) have different applications in Astronomy, including data reduction and data mining. In this work we propose the use ANNs in the identification of stellar model solutions. We illustrate this method, by applying an ANN to the 0.8M$_\odot$ star CG Cyg B. Our ANN was trained using 60,000 different 0.8M$_\odot$ stellar models. With this approach we identify the models which reproduce CG Cyg B's position in the HR diagram. We observe a correlation between the model's initial metal and helium abundance which, in most cases, does not agree with a helium to metal enrichment ratio $Δ$Y/$Δ$Z=2. Moreover, we identify a correlation between the model's initial helium/metal abundance and both its age and mixing-length parameter. Additionally, every model found has a mixing-length parameter below 1.3. This means that CG Cyg B's mixing-length parameter is clearly smaller than the solar one. From this study we conclude that ANNs are well suited to deal with the degeneracy of model solutions of solar type stars.
An Application of Deep Neural Networks in the Analysis of Stellar Spectra
光谱调查需要快速有效的分析方法,以最大限度地发挥其科学影响。在这里,我们应用深度神经网络架构来分析SDSS-III APOGEE DR 13和合成恒星光谱。当我们的卷积神经网络模型(StarNet)在APOGEE光谱上进行训练时,我们表明恒星参数(温度,重力和金属量)的确定具有与APOGEE管道相似的精度和准确性。StarNet还可以在合成数据上进行训练后预测恒星参数,在各种信噪比范围内,APOGEE数据和合成数据都具有出色的精度和准确度。此外,恒星参数测定的统计不确定性与APOGEE管道结果和独立于光谱测定的结果之间的差异相当。我们将StarNet与其他数据驱动的方法进行了比较;例如,StarNet和Cannon 2在使用相同数据集进行训练时表现出类似的行为,但StarNet在原始Cannon使用的小训练集上表现不佳。恒星参数的光谱特征的影响,检查通过偏导数的StarNet模型结果相对于输入光谱。虽然StarNet是使用APOGEE观测光谱和相应的ASSET合成数据开发的,但我们认为这种技术适用于其他波长范围和其他光谱调查。
O-type Stars Stellar Parameter Estimation Using Recurrent Neural Networks
Centro Universitario de Ciencias Economico Administrativas (CUCEA), Universidad de Guadalajara(瓜达拉哈拉大学经济管理科学大学中心(CUCEA));Instituto de Astronomía y Meteorología (IAM), Universidad de Guadalajara(瓜达拉哈拉大学天文与气象研究所(IAM));Escuela Nacional Colegio de Ciencias y Humanidades, Plantel Sur (ENCCH Sur), Universidad Nacional Autónoma de México (UNAM)(墨西哥国立自治大学(UNAM)国立科学与人文学院南校区(ENCCH Sur))
Asteroseismology of solar-like oscillators: emulating individual mode frequencies with a branching neural network
School of Physics & Astronomy, University of Birmingham(伯明翰大学物理与天文学院);Stellar Astrophysics Centre, Department of Physics and Astronomy, Aarhus University(奥胡斯大学物理与天文系恒星天体物理学中心);Advanced Research Computing, University of Birmingham(伯明翰大学高级计算研究中心);Institute for Frontiers in Astronomy and Astrophysics, Beijing Normal University(北京师范大学前沿天文与天体物理研究所);Department of Astronomy, Beijing Normal University(北京师范大学天文系);Sydney Institute for Astronomy, School of Physics, University of Sydney(悉尼大学物理学院悉尼天体物理研究所)
RotNet: Fast and Scalable Estimation of Stellar Rotation Periods Using Convolutional Neural Networks
Intel Labs(英特尔实验室);Massachusetts Institute of Technology(麻省理工学院);NASA Ames Research Center(美国国家航空航天局艾姆斯研究中心);Illinois Institute of Technology(伊利诺伊理工学院);The Catholic University of America(美国天主教大学);University of Oxford(牛津大学);University of Bern(伯尔尼大学);Southwest Research Institute(西南研究院)
Identifying Exoplanets with Deep Learning VI. Enhancing neural network mitigation of stellar activity RV signals with additional metrics
Imperial College London(帝国理工学院);Massachusetts Institute of Technology(麻省理工学院);University of Birmingham(伯明翰大学);Technical University of Denmark(丹麦技术大学);University of St Andrews(圣安德鲁斯大学);Fundación Galileo Galilei—INAF(伽利略基金会-INAF);Observatoire de Genève, Université de Genève(日内瓦天文台,日内瓦大学)
Learning the Stellar Structure Equations via Self-supervised Physics-Informed Neural Networks
SkAI Institute (NSF–Simons AI Institute for the Sky)(SkAI研究所(NSF-西蒙斯天空人工智能研究所));Department of Electrical and Computer Engineering, Northwestern University(西北大学电气与计算机工程系);CIERA, Northwestern University(西北大学CIERA);Department of Physics and Astronomy, Northwestern University(西北大学物理与天文学系);Department of Mathematics, University of Cadiz(加的斯大学数学系);OST Eastern Switzerland University of Applied Sciences(东瑞士应用科学大学);Indian Institute of Technology (IIT) Delhi(印度理工学院德里分校)
Mitigating stellar radial velocity jitter using orthogonal activity indices and a time-aware neural network
Institut de Ciències de l’Espai (ICE, CSIC)(空间科学研究所);Institut d’Estudis Espacials de Catalunya (IEEC)(加泰罗尼亚太空研究所);Facultat de Física, Universitat de Barcelona (UB)(巴塞罗那大学物理学院);University of Warwick(华威大学);Delft University of Technology(代尔夫特理工大学);Barcelona School of Economics(巴塞罗那经济管理学院)
A method to derive self-consistent NLTE astrophysical parameters for 4 million high-resolution 4MOST stellar spectra in half a day with invertible neural networks
Universität Heidelberg(海德堡大学);Max-Planck-Institut für Astronomie(马克斯·普朗克天文学研究所);Leibniz-Institut für Astrophysik Potsdam (AIP)(波茨坦阿诺德·爱因斯坦天体物理研究所)
On the estimation of stellar parameters with uncertainty prediction from Generative Artificial Neural Networks: application to Gaia RVS simulated spectra
Universidade da Coruña (UDC)(拉科鲁尼亚大学);Universidade de Vigo (Uvigo)(维戈大学);Instituto de Astrofísica de Canarias(加那利天体物理研究所);Universidad de La Laguna(拉拉古纳大学)
Generalization from Low- to Moderate-Resolution Spectra with Neural Networks for Stellar Parameter Estimation: A Case Study with DESI
Department of Physics \& Astronomy, The Johns Hopkins University, Baltimore, MD 21218, USA;Department of Astronomy, The Ohio State University, 140 West 18th Avenue, Columbus, OH 43210, USA;Center for Cosmology;AstroParticle Physics (CCAPP), The Ohio State University, Columbus, OH 43210, USA;Department of Computer Science, The Johns Hopkins University, Baltimore, MD 21218, USA;School of Astronomy;Space Science, University of Chinese Academy of Sciences, Beijing 100049, People's Republic of China;National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100012, People's Republic of China;Department of Information Systems, E\"otv\"os Lor\';University, Budapest 1117, Hungary;Department of Applied Mathematics \& Statistics, Johns Hopkins University, Baltimore, MD 21218, USA
The Stellar Observations Network Group (SONG) -- A Legacy Archive of Stellar Time-Domain Spectroscopy
Aarhus University(奥胡斯大学);Instituto de Astrofísica de Canarias(加那利天体物理学研究所);Universidad de La Laguna (ULL)(拉帕鲁纳大学);University of Southern Queensland(南昆士兰大学);National Astronomical Observatories, Chinese Academy of Sciences(中国科学院国家天文台);China West Normal University(西华师范大学)
Identifying Exoplanets with Deep Learning. IV. Removing Stellar Activity Signals from Radial Velocity Measurements Using Neural Networks
Massachusetts Institute of Technology(麻省理工学院);University of Texas at Austin(德克萨斯大学奥斯汀分校);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);Université de Genève(日内瓦大学);Observatoire de Genève(日内瓦天文台);University of St Andrews(圣安德鲁斯大学);Facebook(脸书);Technical University of Denmark(丹麦技术大学);DTU Space, National Space Institute(丹麦技术大学国家空间研究所)
精确径向速度(RV)观测的系外行星探测目前受到恒星活动引入的虚假RV信号的限制。我们表明,线性回归和神经网络等机器学习技术可以有效地从RV观测中去除活动信号(由于星点/光斑)。以前的努力集中在使用高斯过程回归等建模技术及时仔细过滤活动信号(例如Haywood等人2014)。相反,我们系统地去除活动信号,只使用谱线的平均形状的变化,而没有关于何时收集观测结果的信息。我们在模拟数据(使用SOAP 2.0软件生成; Dumusque et al. 2014)和HARPS-N太阳望远镜对太阳的观测(Dumusque et al. 2015; Phillips et al. 2016; Collier Cameron et al. 2019)上训练了我们的机器学习模型。我们发现,这些技术可以预测和删除模拟数据(改善RV散射从82厘米/秒到3厘米/秒)和超过600个实际观测采取了近三年的HARPS-N太阳望远镜(改善RV散射从1.753米/秒到1.039米/秒,约1.7改善的一个因素)。在未来,这些或类似的技术可以从我们太阳系以外的恒星观测中去除活动信号,并最终帮助探测类太阳恒星周围的可居住区地球质量的系外行星。