Atmospheric parameter measurement of Low-S/N stellar spectra based on deep learning
Atmospheric parameter measurement of Low-S/N stellar spectra based on deep learning
复制标题
基于深度学习的低信噪比恒星光谱大气参数测量
DOI：
10.1016/j.ijleo.2020.165004
复制
发表时间：
2020-09
期刊：
影响因子：
3.1
通讯作者：
Bu Yude
中科院分区：
文献类型：
--
作者：
Wu Minglei;Pan Jingchang;Yi Zhenping;Kong Xiaoming;Bu Yude
从恒星光谱中提取准确的大气参数对恒星研究具有重要意义。目前，多元线性回归、人工神经网络、支持向量机等机器学习方法已被广泛应用于大气参数的提取。然而，这些方法一般只适用于高信噪比(高信噪比)(S/N)恒星光谱的大气参数估计。对于低信噪比(低信噪比S/N)的恒星光谱，这些方法往往表现不佳。为了解决这个问题，我们提出了一种一维卷积神经网络StarNet。该方法包括以下三个步骤：首先，选取S/N<；=15的光谱作为输入光谱；其次，通过两个卷积层和一个最大汇聚层从恒星光谱中提取具有代表性的特征；第三，通过两个全连通的层来学习光谱到大气参数的映射函数。我们用Kurucz模型计算的合成光谱和大天空面积多目标光纤光谱望远镜(LAMOST)的观测光谱对该方法进行了评估，并与Lick+OLS和Wavelet+ANN等常用方法进行了比较。实验表明，该方法对低S/N恒星光谱的大气参数估计是有效的，且比其他方法更准确。
Deriving accurate atmospheric parameters from stellar spectra is of fundamental importance for stellar research. At present, machine learning, such as multiple linear regression, artificial neural networks (ANN), and support vector machines, have been widely used to derive atmospheric parameters. However, these methods are generally only applicable to estimate the atmospheric parameters of high signal-to-noise ratio (high-S/N) stellar spectra. For low signal-to-noise ratio (low-S/N) stellar spectra, these methods tend to perform poorly. In order to address the problem, we propose a one-dimensional convolutional neural network StarNet. The proposed method includes the following three steps: firstly, select the spectra with S/N< = 15 as the input spectra; secondly, extract representative features from stellar spectra through two convolutional layers and a max pooling layer; thirdly, learn the mapping function from spectra to atmospheric parameters through two fully connected layers. We evaluate the proposed method on both synthetic spectra calculated from Kurucz models and observed spectra from the Large Sky Area Multi-Object Fiber Spectroscopic Telescope (LAMOST), as well as compare it with other commonly used methods including Lick + OLS and Wavelet + ANN. Experiments show that the proposed method is efficient in estimating the atmospheric parameters of low-S/N stellar spectra and more accurate than other methods.
登录
查看更多内容
影响因子：
3.7
作者：
M. Timmerman
通讯作者：
M. Timmerman
影响因子：
4.8
作者：
Henry W. Leung;J. Bovy
通讯作者：
Henry W. Leung;J. Bovy
影响因子：
3.2
作者：
Abdi, Herve;Williams, Lynne J.
通讯作者：
Williams, Lynne J.
DOI：
10.3847/0004-637x/817/1/78
发表时间：
2016-01
期刊：
The Astrophysical Journal
影响因子：
--
作者：
Yude Bu;Gang Zhao;Jingchang Pan;Y. B. Kumar
通讯作者：
Yude Bu;Gang Zhao;Jingchang Pan;Y. B. Kumar
DOI：
10.3847/2041-8205/826/2/l25
发表时间：
2016-03
期刊：
The Astrophysical Journal Letters
影响因子：
--
作者：
H. Rix;Yuan-Sen Ting (丁源森);C. Conroy;D. Hogg
通讯作者：
H. Rix;Yuan-Sen Ting (丁源森);C. Conroy;D. Hogg