arXiv 1902.059502019-02astro-ph.CO

一种稳健高效的深度学习方法用于星系团的动态质量测量

A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters

Matthew Ho, Markus Michael Rau, Michelle Ntampaka, Arya Farahi, Hy Trac, Barnabas Poczos

备注：: 22 pages, 10 figures, 4 tables, accepted for publication at ApJ
发表信息：: 2019 ApJ, 887, 25
DOI：: 10.3847/1538-4357/ab4f82

摘要：

我们证明了卷积神经网络（CNN）的能力，以减轻系统的维里尺度关系，并产生动态质量估计的星系团具有显着低的偏差和散射。我们提出了两个模型，CNN $_\mathrm{1D}$和CNN $_\mathrm{2D}$，它们利用这种深度学习工具来从成员星系动态分布中推断星系团质量。我们的第一个模型，CNN $_\text{1D}$，直接从成员星系的视线速度分布推断星系团的质量。我们的第二个模型，CNN $_\text{2D}$，扩展了CNN $_\text{1D}$的输入空间，以学习星系视线速度和投影径向距离的联合分布。我们训练每个模型作为集群质量的回归，使用从MultiDark模拟和UniverseMachine目录生成的真实模拟集群观测的标记目录。然后，我们从同一模拟目录中选择一组独立的模拟观测值来评估每个模型的性能。CNN模型产生具有低至$0.132$ dex的离散对数正态残差的聚类质量预测，比经典的$M$ - $σ$幂律估计量提高了2倍以上。此外，相对于类似的机器学习方法，CNN模型将预测分散度降低了高达$17\%$，同时在更短的训练和评估时间内执行（因子为30），并产生更强大的质量预测（在星系采样率变化下提高预测稳定性$30\%$）。

英文摘要：

We demonstrate the ability of convolutional neural networks (CNNs) to mitigate systematics in the virial scaling relation and produce dynamical mass estimates of galaxy clusters with remarkably low bias and scatter. We present two models, CNN$_\mathrm{1D}$ and CNN$_\mathrm{2D}$, which leverage this deep learning tool to infer cluster masses from distributions of member galaxy dynamics. Our first model, CNN$_\text{1D}$, infers cluster mass directly from the distribution of member galaxy line-of-sight velocities. Our second model, CNN$_\text{2D}$, extends the input space of CNN$_\text{1D}$ to learn on the joint distribution of galaxy line-of-sight velocities and projected radial distances. We train each model as a regression over cluster mass using a labeled catalog of realistic mock cluster observations generated from the MultiDark simulation and UniverseMachine catalog. We then evaluate the performance of each model on an independent set of mock observations selected from the same simulated catalog. The CNN models produce cluster mass predictions with lognormal residuals of scatter as low as $0.132$ dex, greater than a factor of 2 improvement over the classical $M$-$σ$ power-law estimator. Furthermore, the CNN model reduces prediction scatter relative to similar machine learning approaches by up to $17\%$ while executing in drastically shorter training and evaluation times (by a factor of 30) and producing considerably more robust mass predictions (improving prediction stability under variations in galaxy sampling rate by $30\%$).

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。

摘要：

英文摘要：

相关论文