论文标题
C2游戏：与机器学习的集群星系会员资格分类
C2-GaMe: Classification of Cluster Galaxy Membership with Machine Learning
论文作者
论文摘要
我们介绍了集群星系成员（C $^2 $ -GAME）的分类，这是一种基于机器学习模型套件的分类算法，该模型使用相位空间信息作为输入，将星系区分为轨道，输入和背景（Interloper）群体，将星系区分为轨道，输入和背景（Interloper）群体。我们基于多黑色Planck 2 N-Body模拟的Universemachine模拟目录中的星系训练和测试C $^2 $游戏。我们表明，概率分类优于确定性分类，在估计簇的物理特性（包括密度曲线和速度分散）时。我们建议一组估计器，以获得群集特性的无偏估计。我们证明，C $^2 $ -GAME可以恢复轨道和插入星系的位置和速度分布的分布，并在预计相位空间中使用跨行者的情况下使用概率预测时使用$ <1 \％$统计错误。此外，我们通过将训练模型应用于不同的模拟来证明训练有素的模型的鲁棒性。最后，随着附加功能提高了分类性能，增加了特定的星形形成速率以及星系光质量与集群光环质量的比率。我们讨论了该技术的潜在应用，以增强群集宇宙学和星系淬火。
We present Classification of Cluster GAlaxy MEmbers (C$^2$-GaMe), a classification algorithm based on a suite of machine learning models that differentiates galaxies into orbiting, infalling, and background (interloper) populations, using phase space information as input. We train and test C$^2$-GaMe with the galaxies from UniverseMachine mock catalog based on Multi-Dark Planck 2 N-body simulations. We show that probabilistic classification is superior to deterministic classification in estimating the physical properties of clusters, including density profiles and velocity dispersion. We propose a set of estimators to get an unbiased estimation of cluster properties. We demonstrate that C$^2$-GaMe can recover the distribution of orbiting and infalling galaxies' position and velocity distribution with $<1\%$ statistical error when using probabilistic predictions in the presence of interlopers in the projected phase space. Additionally, we demonstrate the robustness of trained models by applying them to a different simulation. Finally, adding a specific star formation rate and the ratio of the galaxy's halo mass to the cluster's halo mass as additional features improves the classification performance. We discuss potential applications of this technique to enhance cluster cosmology and galaxy quenching.
