摘要: 天体光谱处理中的一项基本任务是对大量的恒星光谱进行自动分类。到目前为止,恒星光谱的分类工作多是基于一维光谱数据。该研究打破传统的天体光谱数据处理流程,提出了基于二维恒星光谱分类的方法。在LAMOST(the large sky area multi-object fiber spectroscopic telescope)的数据处理流程中,所有的一维光谱都是由二维光谱抽谱、合并得来。二维光谱是由光谱仪产生的图像,包括蓝端图像和红端图像。基于LAMOST二维光谱数据,提出了特征融合卷积神经网络(FFCNN)分类模型,用于二维恒星光谱的分类。该模型是一个有监督的算法,通过两个CNN模型分别提取蓝端图像和红端图像的特征,然后将二者进行融合得到新的特征,再利用CNN对新特征进行分类。所使用的数据全部来源于LAMOST,我们在LMOST DR7中随机选择了一批源,然后获得了它们的二维光谱。一共有14 840根F,G和K型恒星的二维光谱用于FFCNN模型的训练,其中包括7 420根蓝端光谱和7 420根红端光谱。由于三类恒星光谱的数量并不均衡,在训练的过程中分别为每类恒星光谱设置了不同权重,防止模型出现分类失衡现象。同时,为了加快模型收敛,对二维光谱数据采用Z-score归一化处理。此外,为了充分利用所有样本,提高模型的可靠度,采用五折交叉验证的方法验证模型。3 710根二维光谱用作测试集,使用准确率、精确率、召回率和F1-score来对FFCNN模型的性能进行评价。实验结果显示,F,G和K型恒星的精确率分别达到87.6%,79.2%和88.5%,而且它们超过了一维光谱分类的结果。实验结果证明基于FFCNN的二维恒星光谱分类是一种有效的方法,它也为恒星光谱的处理提供了新的思路和方法。
关键词:二维恒星光谱;光谱分类;FFCNN模型;归一化;交叉验证
Abstract:Automatic classification of many stellar spectra is a basic task in celestial spectral processing. So far, the classification of star spectra is based on one-dimensional (1D) spectra. This paper proposes a new method based on two-dimensional(2D) stellar spectral classification. In the data processing process of LAMOST (the Large Sky Area Multi-Object Fiber Spectroscopic Telescope), 1D spectra are extracted and combined with 2D spectra, which are the images produced by a spectrometer, including blue end and red end. Based on LAMOST 2D spectra, a convolutional neural network (FFCNN) classification model is proposed for stellar spectral classification. The model is a supervised algorithm which extracts the features of the blue end and red end respectively through two CNN models. And the model fuses the two features to get new features and uses CNN to classify the new features. The data used in this work are all from LAMOST. A batch of sources are randomly selected in LAMOST DR 7, and their 2D spectra are obtained. There are 14 840 F, G, and K stars in 2D spectra for training the FFCNN model, including 7 420 blue end and 7 420 red end spectra. The number of three kinds of stellar spectra is not balanced. Different weights are set for each kind of stellar spectra in the training process to prevent the classification imbalance. At the same time, to accelerate the model’s convergence, the Z-score normalization method is used for 2D spectra. In addition, five-fold cross-validation is used to improve the model’s sample utilization and reliability. 3 710 2D spectra are used as the test set, and the accuracy, precision, recall and F1-score are used to evaluate the performance of the FFCNN model. Experimental results show that the precision of F, G, and K type stars reach 87.6%, 79.2%, and 88.5%, respectively, and they exceed the results of 1D spectral classification. The experimental results prove that the 2D stellar spectral classification based on FFCNN is an effective method, and it also provides new ideas and methods for the processing of stellar spectra.
逯亚坤,邱 波,罗阿理,郭小雨,王林倩,曹冠龙,白仲瑞,陈建军. 基于FFCNN的二维恒星光谱分类[J]. 光谱学与光谱分析, 2022, 42(06): 1881-1885.
LU Ya-kun, QIU Bo, LUO A-li, GUO Xiao-yu, WANG Lin-qian, CAO Guan-long, BAI Zhong-rui, CHEN Jian-jun. Classification of 2D Stellar Spectra Based on FFCNN. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022, 42(06): 1881-1885.
[1] Chen P, Shan H, Gao Y. Astrophysics and Space Science, 2011, 331:63.
[2] Yao S, Wu X, Li Y, et al. The Astrophysical Journal Supplement Series, 2019, 240:6.
[3] Morgan W, Keenan P. Annual Review of Astronomy and Astrophysics, 1973, 11:29.
[4] Gray R, Corbally C. The Astronomical Journal, 2013, 147: 80.
[5] Fabbro S, Venn K A, et al. Monthly Notices of the Royal Astronomical Society, 2018, 475: 2978.
[6] Hoyle B. Astronomy and Computing, 2016, 16: 34.
[7] Hon M, Stello D, Yu J. Monthly Notices of the Royal Astronomical Society, 2017, 469: 4578.
[8] Schmidhuber J. Neural Networks, 2015, 61: 85.
[9] Liu W, Zhu M, et al. Monthly Notices of the Royal Astronomical Society, 2019, 483:4774.
[10] Zheng Z P, Qiu B, Luo A L. Publications of the Astronomical Society of the Pacific, 2020, 132:024504.
[11] Zou Z, Zhu T, Xu L, et al. Publications of the Astronomical Society of the Pacific, 2020, 132:044503.
[12] Li G, Zhang H, Bai Z. Publications of the Astronomical Society of the Pacific, 2015, 127:552.
[13] He X, Chen Y. IEEE Geoscience and Remote Sensing Letters, 2021, 18(5): 876.
[14] Hang R, Li Z, Liu Q, et al. IEEE Transactions on Geoscience and Remote Sensing, 2021, 59(3): 2281.
[15] Ritter A, Hyde E A, Parker Q A. Publications of the Astronomical Society of the Pacific, 2014,126: 170.