arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.19904astro-ph.GA
收藏

ERGO-ML: 通过对比学习比较IllustrisTNG与HSC星系图像

ERGO-ML: Comparing IllustrisTNG and HSC galaxy images via contrastive learning

Lukas Eisert, Connor Bottrell, Annalisa Pillepich, Rhythm Shimakawa, Vicente Rodriguez-Gomez, Dylan Nelson, Eirini Angeloudi, Marc Huertas-Company

AI总结:

该研究提出ERGO-ML框架,用NNCLR对比学习方法对齐TNG模拟与HSC观测的星系图像表征,验证70%以上模拟星系的真实性并实现观测星系属性推断。

摘要:

现代宇宙学流体动力学星系模拟能提供跨越宇宙时间的数万个具有合理真实度的合成星系。然而,定量评估模拟宇宙与真实宇宙相比的真实程度十分困难。在ERGO-ML(利用机器学习从星系可观测量中提取真实信息)系列的这篇论文中,我们利用对比学习,基于恒星光图像直接对比大样本的模拟星系与观测星系。该方法无需指定汇总统计量,能够充分利用观测数据的全部信息内容。我们使用宇宙学模拟TNG50和TNG100,生成了与真实Hyper Suprime-Cam(HSC,超广域主焦点相机)观测结果相似的、符合巡天真实度的星系模拟数据集。我们的研究聚焦于红移z=0.1-0.4范围内、恒星质量在$10^9$到$10^{12} M_\text{$\text{\textodot}$}$之间的星系,以此评估模拟TNG星系相较于实际HSC观测结果的真实度。我们将自监督对比学习方法NNCLR应用于两个数据集的g、r、i波段图像,得到了一个256维的表征空间,该空间编码了所有相关的星系可观测属性。首先,我们可以通过在这个多维空间中寻找相似图像,识别出与真实星系高度相似的模拟星系。更具价值的是,我们量化了两组图像表征之间的对齐程度,发现大多数($\boldsymbol{\textgreaterrapprox70}\text{per cent}$)TNG星系与观测到的HSC图像对齐良好。但有一部分模拟星系呈现出尺寸更大、Sersic轮廓更陡、Sersic椭率更小、不对称性更高的特征,显得不够真实。我们还通过以模拟TNG星系作为真值来推断真实HSC星系的属性,证明了所得图像表征的实用性。

英文摘要:

Modern cosmological hydrodynamical galaxy simulations provide tens of thousands of reasonably realistic synthetic galaxies across cosmic time. However, quantitatively assessing the level of realism of simulated universes in comparison to the real one is difficult. In this paper of the ERGO-ML series (Extracting Reality from Galaxy Observables with Machine Learning), we utilize contrastive learning to directly compare a large sample of simulated and observed galaxies based on their stellar-light images. This eliminates the need to specify summary statistics and allows to exploit the whole information content of the observations. We produce survey-realistic galaxy mock datasets resembling real Hyper Suprime-Cam (HSC) observations using the cosmological simulations TNG50 and TNG100. Our focus is on galaxies with stellar masses between $10^9$ and $10^{12} M_\odot$ at $z=0.1-0.4$. This allows us to evaluate the realism of the simulated TNG galaxies in comparison to actual HSC observations. We apply the self-supervised contrastive learning method NNCLR to the images from both simulated and observed datasets (g, r, i - bands). This results in a 256-dimensional representation space, encoding all relevant observable galaxy properties. Firstly, this allows us to identify simulated galaxies that closely resemble real ones by seeking similar images in this multi-dimensional space. Even more powerful, we quantify the alignment between the representations of these two image sets, finding that the majority ($\gtrsim 70$ per cent) of the TNG galaxies align well with observed HSC images. However, a subset of simulated galaxies with larger sizes, steeper Sersic profiles, smaller Sersic ellipticities, and larger asymmetries appears unrealistic. We also demonstrate the utility of our derived image representations by inferring properties of real HSC galaxies using simulated TNG galaxies as the ground truth.

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。

↑