arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.09082astro-ph.COastro-ph.IMcs.LG
收藏

基于机器学习的类星体密度功率谱重建

Reconstruction of the Density Power Spectrum from Quasar Spectra using Machine Learning

Michigan Institute for Data Science, University of Michigan(密歇根大学密歇根数据科学研究所);University of Michigan(密歇根大学);Fermi National Accelerator Laboratory(费米国家加速器实验室);Kavli Institute for Cosmological Physics, The University of Chicago(芝加哥大学卡夫利宇宙物理研究所);The University of Chicago(芝加哥大学)

Maria Han Veiga, Xi Meng, Oleg Y. Gnedin, Nickolay Y. Gnedin, Xun Huan

摘要:

我们描述了一种新的端到端的方法,使用机器学习来重建宇宙学密度扰动的功率谱在高红移从观测到的类星体光谱。结构形成的最先进的宇宙学模拟用于生成视线吸收光谱的大型合成数据集,该数据集与沿同一视线的一维流体量配对,例如物质的总密度和中性原子氢的密度。有了这个数据集,我们建立了一系列数据驱动的模型来预测总物质密度的功率谱。我们能够产生的模型,产生重建的波长$k \leq 2 h Mpc^{-1}$的精度约为1%,而在更大的$k$的错误增加。我们展示了达到特定错误率所需的数据样本大小,从而了解达到所需精度需要多少数据。这项工作为开发方法以分析下一代观测设施即将到来的非常大的数据集奠定了基础。

英文摘要:

We describe a novel end-to-end approach using Machine Learning to reconstruct the power spectrum of cosmological density perturbations at high redshift from observed quasar spectra. State-of-the-art cosmological simulations of structure formation are used to generate a large synthetic dataset of line-of-sight absorption spectra paired with 1-dimensional fluid quantities along the same line-of-sight, such as the total density of matter and the density of neutral atomic hydrogen. With this dataset, we build a series of data-driven models to predict the power spectrum of total matter density. We are able to produce models which yield reconstruction to accuracy of about 1% for wavelengths $k \leq 2 h Mpc^{-1}$, while the error increases at larger $k$. We show the size of data sample required to reach a particular error rate, giving a sense of how much data is necessary to reach a desired accuracy. This work provides a foundation for developing methods to analyse very large upcoming datasets with the next-generation observational facilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑