论文标题
搜索类星体的光谱红移时深度学习
Deep Learning in Searching the Spectroscopic Redshift of Quasars
论文作者
论文摘要
在其宇宙学休息框架上研究宇宙学来源对于跟踪紧凑物体的宇宙历史和特性至关重要。鉴于现有望远镜/检测器的数据量不断增加，我们在这里构建具有残留神经网络（RESNET）结构的1-维卷积神经网络（CNN），以估算Sloan数字天空调查IV（SDSSS-IV）dr16 quasar-n-Quass-n-n-Q. dr16 Quass-n-Q. dr16 quass-n-Q. dr16 quass-n-q dr16 quass in a a a a a quasar in a a a quasar in a a a a a iv simble of dr16 quasar in a a a a aim n-quasars（dr16）比率，名为\ code {fnet}。由于其$ 24 $的卷积层以及不同的内核尺寸为$ 500 $，$ 200 $和15美元的重新结构结构，FNET能够通过自我学习过程在整个光谱中发现“ \ textit {local}”和“ \ textit {local}”图案。对于红移的速度差，$ |Δν| <6000〜 \ rm km/s $和98.0 $ \％$，对于$ |Δν| <12000〜 \ rm km/s $，它达到了97.0 $ \％$的准确性。 While \code{QuasarNET}, which is a standard CNN adopted in the SDSS routine and is constructed by 4 convolutional layers (no ResNet structure), with kernel sizes of $10$, to measure the redshift via identifying seven emission lines (\textit{local} patterns), fails in estimating redshift of $\sim 1.3\%$ of visually inspected quasars in DR16Q目录，并为$ |δν| <6000〜 \ rm km/s $和97.9 $ \％$提供97.8 $ \％$，对于$ |δν| <12000〜 \ rm km/s $。因此，FNET提供了与\ code {quasarnet}相似的准确性，但是它适用于更广泛的SDSS光谱，特别是对于那些缺少\ code {quasarnet}利用的清晰发射线的人。 \ code {fnet}的这些属性，以及机器学习的快速预测能力，允许\ code {fnet}成为管道红移估算器的更准确选择，并且可以使其在即将到来的目录中实用，以减少光谱的数量，以进行视觉检查。
Studying the cosmological sources at their cosmological rest-frames is crucial to track the cosmic history and properties of compact objects. In view of the increasing data volume of existing and upcoming telescopes/detectors, we here construct a 1--dimensional convolutional neural network (CNN) with a residual neural network (ResNet) structure to estimate the redshift of quasars in Sloan Digital Sky Survey IV (SDSS-IV) catalog from DR16 quasar-only (DR16Q) of eBOSS on a broad range of signal-to-noise ratios, named \code{FNet}. Owing to its $24$ convolutional layers and the ResNet structure with different kernel sizes of $500$, $200$ and $15$, FNet is able to discover the "\textit{local}" and "\textit{global}" patterns in the whole sample of spectra by a self-learning procedure. It reaches the accuracy of 97.0$\%$ for the velocity difference for redshift, $|Δν|< 6000~ \rm km/s$ and 98.0$\%$ for $|Δν|< 12000~ \rm km/s$. While \code{QuasarNET}, which is a standard CNN adopted in the SDSS routine and is constructed by 4 convolutional layers (no ResNet structure), with kernel sizes of $10$, to measure the redshift via identifying seven emission lines (\textit{local} patterns), fails in estimating redshift of $\sim 1.3\%$ of visually inspected quasars in DR16Q catalog, and it gives 97.8$\%$ for $|Δν|< 6000~ \rm km/s$ and 97.9$\%$ for $|Δν|< 12000~ \rm km/s$. Hence, FNet provides similar accuracy to \code{QuasarNET}, but it is applicable for a wider range of SDSS spectra, especially for those missing the clear emission lines exploited by \code{QuasarNET}. These properties of \code{FNet}, together with the fast predictive power of machine learning, allow \code{FNet} to be a more accurate alternative for the pipeline redshift estimator and can make it practical in the upcoming catalogs to reduce the number of spectra to visually inspect.
