共查询到18条相似文献，搜索用时 250 毫秒
1.
天体光谱分类是天文学研究的重要内容之一,其关键是从光谱数据中选择和提取对分类识别最有效的特征构建特征空间.提出一种新的基于2维傅里叶谱图像的特征提取方法,并应用于LAMOST (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope)恒星光谱数据的分类研究中.光谱数据来源于LAMOST Data Release 5(DR5),选取30000条F、 G和K型星光谱数据,利用短时傅里叶变换(Short-Time Fourier Transform, STFT)将1维光谱数据变换成2维傅里叶谱图像,对得到的2维傅里叶谱图像采用深度卷积网络模型进行分类,得到的分类准确率是92.90%.实验结果表明通过对LAMOST恒星光谱数据进行STFT可得到光谱的2维傅里叶谱图像,谱图像构成了新的光谱数据特征和特征空间,新的特征对于光谱数据分类是有效的.此方法是对光谱分类的一种全新尝试,对海量天体光谱的分类和挖掘处理有一定的开创意义. 相似文献
2.
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. 相似文献
3.
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. 相似文献
4.
本文提供了１２５颗ＭＫ标准星的ＣＣＤ光谱,光谱型从Ｏ到Ｍ,光度级从Ｖ到Ⅰ,构成较完整的二元分类框架,光谱覆盖范围由传统蓝紫区延伸到黄红区．初步考察和归纳了黄红区适于恒星分类的主要光谱特征和判据．这些结果对于采用相似分辨率的恒星光谱分类工作是非常有用的． 相似文献
5.
本提供了１２５颗ＭＫ标准星的ＣＣＤ光谱，光谱型从Ｏ到Ｍ〉光度级从Ｖ到Ｉ，构成较完整的二元分类框架，光谱覆盖范围由传统蓝紫区延伸到黄红区，初步考察和归纳了黄红区适于恒星分类的主要光谱特征和判据，这些结果对于采用相似分辨率的恒星光谱分类工作是非常有用的。 相似文献
6.
针对目前从海量的快速射电暴(Fast Radio Burst, FRB)候选体中人工筛选FRB事件难以为继的现状,提出了一种基于卷积神经网络(Convolutional Neural Networks, CNN)的FRB候选体分类方法.首先,通过真实的观测数据和仿真FRB组成训练和测试样本集.其次,建立了二输入的深度卷积神经网络模型,并对其进行训练、测试和优化,获取FRB候选体分类器.最后,利用来自脉冲星的单脉冲数据对该分类器的有效性和性能进行了验证.实验结果表明,该方法可以快速从大量候选体中准确识别出单脉冲事件,极大地提高了FRB候选体的处理速率和效率. 相似文献
7.
将未编目的空间碎片正确分类是空间态势感知的重要组成部分. 基于光变曲线, 通过仿真和实测实验, 探讨了空间碎片基本类型的机器学习分类方法. 在数据集中的仿真光变来自形状或材料不同的4类碎片, 实测光变从Mini-Mega TORTORA (MMT)数据库中提取, 实验以深度神经网络作为分类模型, 并和其他机器学习方法进行了比较. 结果显示深度卷积网络优于其他算法, 在仿真实验中对不同材料的圆柱体都能准确识别, 对其余两类卫星的识别率在90%左右; 实测实验中对火箭体和失效卫星的2分类准确率超过99%, 然而在进一步的型号/平台分类中, 准确率有所降低. 相似文献
8.
《天文研究与技术》2020,(1)
天体光谱数据的智能处理正由传统机器学习方法逐步转向深度学习,主要采用基于计算机视觉的技术手段。基于计算机视觉领域广泛应用的DenseNet网络结构,针对光谱数据进行修改,建立了适用于光谱数据的一维卷积神经网络模型,解决天体光谱数据分类任务。在验证数据集上,恒星、星系、类星体的F1分数达到了0.998 7、0.912 7、0.914 7,高于传统的神经网络。光谱分类关注区域的可视化结果表明,本文模型可以学习到各类天体对应的特征谱线,具有较强的可解释性。本文方法被用于阿里云天池天文数据挖掘大赛——天体光谱智能分类,并在843支参赛队伍的3次数据评比中获得了2次第一、1次第三的成绩,证明了该模型在保证分类精度的同时,具有极强的鲁棒性、泛化性,适用于光谱的自动分类。 相似文献
9.
从观测上测定早型星系中恒星形成活动随红移的演化有助于理解这类星系的形成演化.结合GEMS（Galaxy Evolution from Morphology and SEDs）巡天的HST/ACS（Hubble Space Telescope/Advanced Camera for Surveys）高分辨图像和CDFS（ChandraDeep Field South）天区Spitzer、GALEX（Galaxy Evolution Explorer）等多波段数据,基于形态、颜色和恒星质量选出一个0.2≤z≤1.0红移范围的包含456个早型星系的完备样本.利用stacking技术测量了样本星系紫外与红外平均光度,估计早型星系的恒星形成率.结果显示,早型星系中的恒星形成率较低(<3 M⊙·yr-1),随红移递减而降低.在红移z=1以来的恒星形成贡献的质量小于15%.星族分析亦肯定大质量早型星系的主体星族形成于宇宙早期（z>2）. 相似文献
10.
随着天文探测技术的快速发展, 海量的星系图像数据不断产生, 能够及时高效地对星系图像进行形态分类对研究星系的形成与演化至关重要. 针对传统的星系形态分类模型特征选择困难、分类速度慢、准确率受限等难题, 提出一种以Inception-v3神经网络为主干结构, 融合压缩激励(Squeeze and Excitation Network, SE)通道注意力机制的星系形态分类模型. 该模型在斯隆数字巡天(Sloan Digital Sky Survey, SDSS)样本的测试集准确率高达99.37%. 旋涡星系、圆形星系、中间星系、雪茄状星系与侧向星系的F1值分别为99.33%、99.58%、99.33%、99.41%与99.16%. 该模型与Inception-v3、MobileNet (Mobile Neural Network)和ResNet (Residual Neural Network)网络模型相比, SE-Inception-v3宽度和深度优势表现出更强的特征提取能力, 可以高效识别不同形态的星系, 为未来大型巡天计划的大规模星系形态分类问题提供了一种新方法. 相似文献
11.
M. Ammler‐von Eiff D. Sebastian E. W. Guenther B. Stecklum J. Cabrera 《Astronomische Nachrichten》2015,336(2):134-144
Planetary transits detected by the CoRoT mission can be mimicked by a low‐mass star in orbit around a giant star. Spectral classification helps to identify the giant stars and also early‐type stars which are often excluded from further follow‐up. We study the potential and the limitations of low‐resolution spectroscopy to improve the photometric spectral types of CoRoT candidates. In particular, we want to study the influence of the signal‐to‐noise ratio (SNR) of the target spectrum in a quantitative way. We built an own template library and investigate whether a template library from the literature is able to reproduce the classifications. Including previous photometric estimates, we show how the additional spectroscopic information improves the constraints on spectral type. Low‐resolution spectroscopy (R ≈ 1000) of 42 CoRoT targets covering a wide range in SNR (1–437) and of 149 templates was obtained in 2012–2013 with the Nasmyth spectrograph at the Tautenburg 2 m telescope. Spectral types have been derived automatically by comparing with the observed template spectra. The classification has been repeated with the external CFLIB library. The spectral class obtained with the external library agrees within a few sub‐classes when the target spectrum has a SNR of about 100 at least. While the photometric spectral type can deviate by an entire spectral class, the photometric luminosity classification is as close as a spectroscopic classification with the external library. A low SNR of the target spectrum limits the attainable accuracy of classification more strongly than the use of external templates or photometry. Furthermore we found that low‐resolution reconnaissance spectroscopy ensures that good planet candidates are kept that would otherwise be discarded based on photometric spectral type alone. (© 2015 WILEY‐VCH Verlag GmbH & Co. KGaA, Weinheim) 相似文献
12.
F. C. Riddick P. F. Roche P. W. Lucas 《Monthly notices of the Royal Astronomical Society》2007,381(3):1067-1076
The spectral type is a key parameter in calibrating the temperature which is required to estimate the mass of young stars and brown dwarfs. We describe an approach developed to classify low-mass stars and brown dwarfs in the Trapezium Cluster using red optical spectra, which can be applied to other star-forming regions. The classification uses two methods for greater accuracy: the use of narrow-band spectral indices which rely on the variation of the strength of molecular lines with spectral type and a comparison with other previously classified young, low-mass objects in the Chamaeleon I star-forming region. We have investigated and compared many different molecular indices and have identified a small number of indices which work well for classifying M-type objects in nebular regions. The indices are calibrated for young, pre-main-sequence objects whose spectra are affected by their lower surface gravities compared with those on the main sequence. Spectral types obtained are essentially independent of both reddening and nebular emission lines.
Confirmation of candidate young stars and brown dwarfs as bona fide cluster members may be accomplished with moderate resolution spectra in the optical region by an analysis of the strength of the gravity-sensitive Na doublet. It has been established that this feature is much weaker in these very young objects than in field dwarfs. A sodium spectral index is used to estimate the surface gravity and to demonstrate quantitatively the difference between young (1–2 Myr) objects, and dwarf and giant field stars. 相似文献
Confirmation of candidate young stars and brown dwarfs as bona fide cluster members may be accomplished with moderate resolution spectra in the optical region by an analysis of the strength of the gravity-sensitive Na doublet. It has been established that this feature is much weaker in these very young objects than in field dwarfs. A sodium spectral index is used to estimate the surface gravity and to demonstrate quantitatively the difference between young (1–2 Myr) objects, and dwarf and giant field stars. 相似文献
13.
《Chinese Astronomy and Astrophysics》2021,45(3):352-363
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. 相似文献
14.
The 2dF Galaxy Redshift Survey: the dependence of galaxy clustering on luminosity and spectral type 总被引：1，自引：0，他引：1
Peder Norberg Carlton M. Baugh Ed Hawkins Steve Maddox Darren Madgwick Ofer Lahav Shaun Cole Carlos S. Frenk Ivan Baldry Joss Bland-Hawthorn Terry Bridges Russell Cannon Matthew Colless Chris Collins Warrick Couch Gavin Dalton Roberto De Propris Simon P. Driver George Efstathiou Richard S. Ellis Karl Glazebrook Carole Jackson Ian Lewis Stuart Lumsden John A. Peacock Bruce A. Peterson Will Sutherland Keith Taylor 《Monthly notices of the Royal Astronomical Society》2002,332(4):827-838
We investigate the dependence of galaxy clustering on luminosity and spectral type using the 2dF Galaxy Redshift Survey (2dFGRS). Spectral types are assigned using the principal-component analysis of Madgwick et al. We divide the sample into two broad spectral classes: galaxies with strong emission lines ('late types') and more quiescent galaxies ('early types'). We measure the clustering in real space, free from any distortion of the clustering pattern owing to peculiar velocities, for a series of volume-limited samples. The projected correlation functions of both spectral types are well described by a power law for transverse separations in the range 2<( σ / h -1 Mpc)<15 , with a marginally steeper slope for early types than late types. Both early and late types have approximately the same dependence of clustering strength on luminosity, with the clustering amplitude increasing by a factor of ∼2.5 between L * and 4 L *. At all luminosities, however, the correlation function amplitude for the early types is ∼50 per cent higher than that of the late types. These results support the view that luminosity, and not type, is the dominant factor in determining how the clustering strength of the whole galaxy population varies with luminosity. 相似文献
15.
Coryn A. L. Bailer-Jones Mike Irwin & Ted von Hippel 《Monthly notices of the Royal Astronomical Society》1998,298(2):361-377
We investigate the application of neural networks to the automation of MK spectral classification. The data set for this project consists of a set of over 5000 optical (3800–5200 Å) spectra obtained from objective prism plates from the Michigan Spectral Survey. These spectra, along with their two-dimensional MK classifications listed in the Michigan Henry Draper Catalogue, were used to develop supervised neural network classifiers. We show that neural networks can give accurate spectral type classifications (σ68 = 0.82 subtypes, σrms = 1.09 subtypes) across the full range of spectral types present in the data set (B2–M7). We show also that the networks yield correct luminosity classes for over 95 per cent of both dwarfs and giants with a high degree of confidence. Stellar spectra generally contain a large amount of redundant information. We investigate the application of principal components analysis (PCA) to the optimal compression of spectra. We show that PCA can compress the spectra by a factor of over 30 while retaining essentially all of the useful information in the data set. Furthermore, it is shown that this compression optimally removes noise and can be used to identify unusual spectra. This paper is a continuation of the work carried out by von Hippel et al. (Paper I). 相似文献
16.
An automated spectral classification technique for large sky surveys is pro-posed. We firstly perform spectral line matching to determine redshift candidates for an observed spectrum, and then estimate the spectral class by measuring the similarity be-tween the observed spectrum and the shifted templates for each redshift candidate. As a byproduct of this approach, the spectral redshift can also be obtained with high accuracy. Compared with some approaches based on computerized learning methods in the liter-ature, the proposed approach needs no training, which is time-consuming and sensitive to selection of the training set. Both simulated data and observed spectra are used to test the approach; the results show that the proposed method is efficient, and it can achieve a correct classification rate as high as 92.9%, 97.9% and 98.8% for stars, galaxies and quasars, respectively. 相似文献
17.
18.
Ferdinando Patat Stefano Benetti Enrico Cappellaro Massimo Turatto 《Monthly notices of the Royal Astronomical Society》2006,369(4):1949-1960
In this paper, we present and discuss the effects of scattered light echoes (LEs) on the luminosity and spectral appearance of Type Ia supernovae (SNe). After introducing the basic concept of LE spectral synthesis by means of LE models and real observations, we investigate the deviations from pure SN spectra, light and colour curves, the signatures that witness the presence of an LE and the possible inferences on the extinction law. The effects on the photometric parameters and spectral features are also discussed. In particular, for the case of circumstellar dust, LEs are found to introduce an apparent relation between the post-maximum decline rate and the absolute luminosity, which is most likely going to affect the well-known Pskowski–Phillips relation. 相似文献