基于胶囊网络的恒星光谱分类研究

大型巡天项目的快速发展,产生大量的恒星光谱数据,也使得实现恒星光谱数据的自动分类成为一项具有挑战性的工作.提出一种新的基于胶囊网络的恒星光谱分类方法,首先利用1维卷积网络和短时傅里叶变换将来源于LAMOST(Large Sky Area Multi-Object Fiber Spectroscopy Telescope)Data Release 5(DR5)的F5、G5、K5型1维恒星光谱转化成2维傅里叶谱图像,再通过胶囊网络对2维谱图像进行自动分类.由于胶囊网络具有保留图像中实体之间的分层位姿关系和无需池化层的优点,实验结果表明:胶囊网络具有较好的分类性能,对于F5、G5、K5型恒星光谱的分类,准确率优于其他分类方法.     

基于卷积神经网络的恒星光谱型和光度型的分类模型

恒星光谱分类是天文学中一个重要的研究问题.对于已经采集到的海量高维恒星光谱数据的分类,采用模式匹配方法对光谱型分类较为成功,但其缺点在于标准恒星模版之间的差异性在匹配实际观测数据中不能体现出来,尤其是当需要进行光谱型和光度型的二元分类时模版匹配法往往会失败.而采用谱线特征测量的光度型分类强烈地依赖谱线拟合的准确性.为了解决二元分类的问题,介绍了一种基于卷积神经网络的恒星光谱型和光度型分类模型(Classification model of Stellar Spectral type and Luminosity type based on Convolution Neural Network, CSSL CNN).这一模型使用卷积神经网络来提取光谱的特征,通过注意力模块学习到了重要的光谱特征,借助池化操作降低了光谱的维度并压缩了模型参数的数量,使用全连接层来学习特征并对恒星光谱进行分类.实验中使用了大天区面积多目标光纤光谱天文望远镜(Large Sky Area Multi-Object Fiber Spectroscopy Telescope, LAMOST)公开数据集Data Release 5 (DR5,用了其中71282条恒星光谱数据,每条光谱包含了3000多维的特征)对该模型的性能进行验证与评估.实验结果表明,基于卷积神经网络的模型在恒星的光谱型分类上准确率达到92.04%,而基于深度神经网络的模型(Celestial bodies Spectral Classification Model, CSC Model)只有87.54%的准确率; CSSL CNN在恒星的光谱型和光度型二元分类上准确率达到83.91%,而模式匹配方法MKCLASS仅有38.38%的准确率且效率较低.     

猎户座分子云团中弥散电离介质的视向速度及线强度比分布

恒星形成区是研究恒星形成物理过程最重要的天体物理实验室. 猎户座分子云团是研究各种质量恒星形成和相关年轻恒星性质的一个著名天区. 通过对恒星形成区的光学光谱分析, 可以获取其内部热电离气体的运动学和化学性质. 基于国家大科学装置郭守敬望远镜(LAMOST)的光谱观测数据, 从LAMOST I期光谱巡天数据中筛选出8个指向猎户座分子云团的观测面板, 获取了1300多条针对猎户座分子云团内弥散电离介质的有效光谱. 选取不受星际介质污染的背景天光光谱构建超级天光, 对这些光谱数据做减天光处理, 并进一步测量其发射线性质，包括Ha、N Ⅱ] λ 6584、[S Ⅱ]λλ 6717和6731等发射线的中心波长和积分流量等.最后给出猎户座分子云团内弥散电离介质的视向速度和线强度比分布情况.     

恒星大气物理参量的非参数估计方法

恒星大气物理参量（有效温度、表面重力、化学丰度）是导致恒星光谱差异的主要因素．恒星大气物理参量的自动测量是LAMOST等大规模巡天望远镜所产生的海量天体光谱数据自动处理中一个重要研究内容．针对测量大样本的恒星光谱数据估计每个恒星的大气物理参量，提出了一种基于变窗宽核函数的估计算法：变窗宽算法是对固定窗宽算法的改进，分为3个步骤：（1）将历史恒星光谱数据进行PCA处理，得到光谱的低维特征数据；（2）利用特征数据与其物理参数的对应关系，建立一种变窗宽的非参数估计模型；（3）利用该估计模型，直接计算待测恒星光谱的3个物理参量（有效温度、表面重力、金属丰度）．实验结果表明：该方法与固定窗宽估计模型以及在其他文献中报道的方法相比，具有较高的估计精度和鲁棒性．     

基于深度学习的LAMOST光谱分类研究

光谱分类不仅对理解恒星物理学有着重要意义,而且在研究银河系整体结构和演化过程中起着至关重要的作用.然而在相关研究中仍存在分类精度低和光谱型未知等问题,因此提出一种新的光谱自动分类模型并将其应用在F、G和K 3种恒星光谱的分类中,方法的基本思想是训练一个深度信念网络对光谱数据进行分层特征学习,然后采用反向传播算法对整个模型进行微调.从LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope) Data Release 5 (DR5)中选取31667条包含F、G和K 3种恒星的光谱数据,并在TOPCAT软件中与GAIA (Global Astrometric Interferometer for Astrophysics)数据进行交叉,得到颜色-星等图并验证光谱数据的分布.最后对该模型进行评估,结果表明:深度信念网络在综合性能上优于其他分类算法.     

富锂巨星研究概述

锂(Li)元素最初诞生于大爆炸核合成,是最重要的轻元素之一.但锂元素丰度在很多类天体中均表现出观测与理论不符的现象,这一问题困扰了天体物理学家数十年.富锂巨星就是这样的一类天体,它们大气中的Li丰度超过了标准恒星演化模型的理论值.虽然富锂巨星早在约四十年前就被发现,但其起源依然是未解之谜.随着以郭守敬望远镜(LAMOST)巡天等为代表的大型光谱巡天项目的开展、以开普勒(Kepler)卫星为代表的星震学观测数据的产出以及数据驱动类方法和技术的飞速发展,针对富锂巨星的研究取得了一系列重要的突破.在此将回顾富锂巨星近四十年来的研究进展,并总结对于富锂巨星最新的认知.     

GD-1星流金属丰度与运动特性分析

星流在星系形成与演化过程中扮演了重要的角色,对银河系中星流的研究将有助于进一步探究银河系的合并历史.将LAMOST(Large Sky Area Multi-Object Fiber Spectroscopic Telescope)DR6光谱数据以及SDSS(Sloan Digital Sky Survey)DR12光谱数据分别与Gaia(Global Astrometric Interferometer for Astrophysics)DR2天体测量数据交叉匹配,获得恒星自行等数据.对GD-1星流在速度空间、几何空间和金属丰度上进行限制,从LAMOST DR6和SDSS DR12数据中共获得了157颗星流成员星.GD-1星流的平均金属丰度为[Fe/H]=-2.16±0.10 dex,延伸长度超过80°.收集前人给出的GD-1星流高概率成员星,组成较大的成员星样本进行对比分析,发现GD-1星流的金属丰度分布呈现内低外高的特点,沿着星流方向径向速度分布特点是两端大、中间小,?₁=-20°(?₁为GD-1星流坐标系横坐标)和?₁=-60°附近的间隙是因为成员星运动差异形成的.根据成员星分布及其速度分布特性,推测GD-1星流起源位置是在?₁=-40°附近.     

The Cannon:一种基于光谱数据的恒星参数测量方法

新一代大规模光谱巡天项目产生了近千万条低分辨率恒星光谱,基于这些光谱数据,介绍一种名为The Cannon的机器学习方法。该方法完全基于已知恒星大气参数(有效温度、表面重力加速度和金属丰度等)的光谱数据,通过数据驱动来构建特征向量,建立光谱流量特征和恒星参数的函数对应关系,进而应用到观测光谱数据中,实现对恒星光谱的大气参数求解。The Cannon的主要优势为不直接基于任何恒星物理模型,适用性更广;由于使用了全谱信息,即便对于低信噪比光谱也能得到较高可信度的参数结果,该算法在大规模恒星光谱的数据处理和参数求解方面具有明显的优势。此外,还利用The Cannon得到LAMOST光谱数据中K巨星和M巨星的恒星参数。     

使用SOFM方法进行恒星光谱自动分类

ＳＯＦＭ是人工神经网络的非监督算法,可以将数据组织到一个特征图上,而保存大多数原始数据空间的拓扑特征,使用这种方法进行恒星光谱自动分类,分类结果与哈佛序列十分相似,ＳＯＦＭ方法应该是进行大数量恒星光谱样本在线分类的有用方法,它能够自动执行,因此可用于处理大数量天体光谱。     

使用SOFM方法进行恒星光谱自动分类

ＳＯＦＭ是人工神经网络的非监督学习算法,可以将数据组织到一个特征图上,而保存 大多数原始数据空间的拓扑特征．使用这种方法进行恒星光谱自动分类,分类结果与哈佛 序列十分相似．ＳＯＦＭ方法应该是进行大数量恒星光谱样本在线分类的有用方法,它能 够自动执行,因此可用于处理大数量天体光谱．     

Stellar Spectral Classification Based on Capsule Network

The rapid development of large-scale sky survey project has produced a large amount of stellar spectral data, which make the automatic classification of stellar spectral data a challenging task. In this paper, we have proposed a stellar spectral classification method based on a capsule network. At first, by using the one-dimensional convolutional network and short-time Fourier transform (STFT), the one-dimensional spectra of the F5, G5, and K5 types selected from the LAMOST Data Release 5 (DR5) are converted into the two-dimensional Fourier spectrum images. Then, the two-dimensional Fourier spectrum images are classified automatically by the capsule network. Because the capsule network can preserve the hierarchical pose relationships among the entities in the image, and it does not need any pooling layers, the experimental results show that the capsule network has a better classification performance, for the classifications of the F5, G5, and K5-type stellar spectra, its classification accuracy is superior to other classification methods.     

Stellar spectral classification and feature evaluation based on a random forest

With the availability of multi-object spectrometers and the design and operation of some large scale sky surveys, the issue of how to deal with enormous quantities of spectral data efficiently and accurately is becoming more and more important. This work investigates the classification problem of stellar spectra under the assumption that there is no perfect absolute flux calibration, for example, when considering spectra from the Guo Shou Jing Telescope(the Large Sky Area Multi-Object Fiber Spectroscopic Telescope, LAMOST). The proposed scheme consists of the following two procedures: Firstly, a spectrum is normalized based on a 17 th order polynomial fitting; secondly, a random forest(RF) is utilized to classify the stellar spectra. Experiments on four stellar spectral libraries show that the RF has good classification performance. This work also studied the spectral feature evaluation problem based on RF. The evaluation is helpful in understanding the results of the proposed stellar classification scheme and exploring its potential improvements in the future.     

Automated Separation of Stars and Normal Galaxies Based on Statistical Mixture Modeling with RBF Neural Networks

For LAMOST, the largest sky survey program in China, the solution of the problem of automatic discrimination of stars from galaxies by spectra has shown that the results of the PSF test can be significantly refined. However, the problem is made worse when the redshifts of galaxies are not available. We present a new automatic method of star/(normal) galaxy separation, which is based on Statistical Mixture Modeling with Radial Basis Function Neural Networks (SMM-RBFNN). This work is a continuation of our previous one, where active and non-active celestial objects were successfully segregated. By combining the method in this paper and the previous one, stars can now be effectively separated from galaxies and AGNs by their spectra-a major goal of LAMOST, and an indispensable step in any automatic spectrum classification system. In our work, the training set includes standard stellar spectra from Jacoby's spectrum library and simulated galaxy spectra of EO, SO, Sa, Sb types with redshift ranging from 0 to 1     

基于深度学习的LAMOST星系星族参数测量

星系的光谱包含其内部恒星的年龄和金属丰度等信息, 从观测光谱数据中测量这些信息对于深入了解星系的形成和演化至关重要. LAMOST (Large Sky Area Multi-Object Fiber Spectroscopic Telescope)巡天发布了大量的星系光谱, 这些高维光谱与它们的物理参数之间存在着高度的非线性关系. 而深度学习适合于处理多维、海量的非线性数据, 因此基于深度学习技术构建了一个8个卷积层$+$4个池化层$+$1个全连接层的卷积神经网络, 对LAMOST Data Release 7 (DR7)星系的年龄和金属丰度进行自动估计. 实验结果表明, 使用卷积神经网络通过星系光谱预测的星族参数与传统方法基本一致, 误差在0.18dex以内, 并且随着光谱信噪比的增大, 预测误差越来越小. 实验还对比了卷积神经网络与随机森林回归模型、深度神经网络的参数测量结果, 结果表明卷积神经网络的结果优于其他两种回归模型.     

A Method of Estimating the [α/Fe] Ratios from Low-resolution Stellar Spectratwo

A method for the determination of [α/Fe] from low-resolution stellar spectra is presented. The proposed scheme includes the following three steps: firstly, the spectrum is decomposed by the multi-scale Haar wavelet, and the high-frequency components are removed to suppress the high-frequency noise; then, based on the correlation of the spectral data component with [α/Fe], the spectral features are selected by the LASSO (Least Absolute Shrinkage and Selection Operator) algorithm; finally, [α/Fe] is measured by the multiple linear regression method based on the MARCS stellar spectrum library. The effectiveness of the method is verified with the low-resolution stellar spectra of ELODIE, SDSS (Sloan Digital Sky Survey), LAMOST (Large Sky Area Multi-Object Fibre Spectroscopic Telescope), and four star clusters. The systematic deviations and accuracies are as follows: (0.04 dex, 0.064 dex) for the 317 ELODIE spectra; (0.16 dex, 0.065 dex) for the 412 SDSS spectra; (0.05 dex, 0.062 dex) for the 1276 LAMOST spectra (with the signal-noise ratio in the g band (SNRG) greater than 20). The averages of [α/Fe] obtained for the likely members of the globular star clusters (M13, M15) and open star clusters (NGC2420, M67) are in agreement with the literature values.     

基于数据仓库的星系光谱分类

大天区面积多目标光纤光谱天文望远镜(LAMOST)将被建成,会产生大量的星系光谱数据。根据天文数据的积累过程,我们设计基于数据仓库的星系光谱分类系统。文章首先介绍了星系光谱的特征,数据仓库的特点,在此基础上描述了建立基于数据仓库的星系光谱自动分类系统的步骤,并给出对该系统进行测试的结果。     

Spectral classification of stars based on LAMOST spectra

In this work, we select spectra of stars with high signal-to-noise ratio from LAMOST data and map their MK classes to the spectral features. The equivalent widths of prominent spectral lines, which play a similar role as multi-color photometry, form a clean stellar locus well ordered by MK classes. The advantage of the stellar locus in line indices is that it gives a natural and continuous classification of stars consistent with either broadly used MK classes or stellar astrophysical parameters. We also employ an SVM-based classification algorithm to assign MK classes to LAMOST stellar spectra. We find that the completenesses of the classifications are up to 90% for A and G type stars, but they are down to about 50% for OB and K type stars. About 40% of the OB and K type stars are mis-classified as A and G type stars,respectively. This is likely due to the difference in the spectral features between late B type and early A type stars or between late G and early K type stars being very weak. The relatively poor performance of the automatic MK classification with SVM suggests that the direct use of line indices to classify stars is likely a more preferable choice.