arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.10577astro-ph.COastro-ph.IMcs.AIcs.LG
收藏

对宇宙学结构形成的深度学习见解

Deep learning insights into cosmological structure formation

Max-Planck-Institut für Astrophysik(马克斯·普朗克天体物理研究所);University College London(伦敦大学学院);Stockholm University(斯德哥尔摩大学);Fermi National Accelerator Laboratory(费米国家加速器实验室);University of Chicago(芝加哥大学);Rutherford Appleton Laboratory(卢瑟福·阿普尔顿实验室)

Luisa Lucie-Smith, Hiranya V. Peiris, Andrew Pontzen, Brian Nord, Jeyan Thiyagalingam

AI总结:

本研究构建三维卷积神经网络分析初始条件,发现各向异性信息对暗物质晕最终质量预测的提升有限,证明各向同性信息已基本饱和,并指出引入近似动力学信息是更有效的预测途径。

摘要:

早期宇宙中存在的线性初始条件在晚期演化为暗物质晕的过程,可以通过宇宙学模拟来计算。然而,对这一复杂过程的理论理解仍然难以捉摸;特别是,初始条件中的各向异性信息在确立暗物质晕最终质量中的作用,一直是一个长期存在的谜题。在此,我们构建了一个深度学习框架来研究这个问题。我们训练了一个三维卷积神经网络(CNN),利用初始条件预测暗物质晕的质量,并完全一般性地量化了初始密度场的各向同性和各向异性方面关于最终暗物质晕质量的信息量。我们发现,相比于密度场的球面平均所包含的关于最终暗物质晕质量的信息,各向异性增加了一小部分信息,尽管这一信息量在统计上是显著的。然而,最终质量预测的整体散度并没有随着这些额外信息发生定性改变,仅从0.9 dex降至0.7 dex。鉴于这种微小的改进,我们的结果表明,初始密度场的各向同性方面基本上饱和了关于最终暗物质晕质量的相关信息。因此,与其寻找直接编码在初始条件各向异性中的信息,不如基于微扰理论等方法添加近似的动力学信息,这才是实现准确、快速的暗物质晕质量预测的更有希望的途径。更广泛地说,我们的结果表明,深度学习框架可以作为一个强大的工具,用于提取对宇宙学结构形成的物理见解。

英文摘要:

The evolution of linear initial conditions present in the early universe into extended halos of dark matter at late times can be computed using cosmological simulations. However, a theoretical understanding of this complex process remains elusive; in particular, the role of anisotropic information in the initial conditions in establishing the final mass of dark matter halos remains a long-standing puzzle. Here, we build a deep learning framework to investigate this question. We train a three-dimensional convolutional neural network (CNN) to predict the mass of dark matter halos from the initial conditions, and quantify in full generality the amounts of information in the isotropic and anisotropic aspects of the initial density field about final halo masses. We find that anisotropies add a small, albeit statistically significant amount of information over that contained within spherical averages of the density field about final halo mass. However, the overall scatter in the final mass predictions does not change qualitatively with this additional information, only decreasing from 0.9 dex to 0.7 dex. Given such a small improvement, our results demonstrate that isotropic aspects of the initial density field essentially saturate the relevant information about final halo mass. Therefore, instead of searching for information directly encoded in initial conditions anisotropies, a more promising route to accurate, fast halo mass predictions is to add approximate dynamical information based e.g. on perturbation theory. More broadly, our results indicate that deep learning frameworks can provide a powerful tool for extracting physical insight into cosmological structure formation.

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。

↑