The CAMELS Project: Cosmology and Astrophysics with Machine-learning Simulations
The CAMELS Project: Cosmology and Astrophysics with Machine-learning Simulations
复制标题
DOI：
10.3847/1538-4357/abf7ba
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
F. Villaescusa-Navarro;D. Anglés-Alcázar;S. Genel;D. Spergel;Rachel S. Somerville;R. Davé;A. Pillepich;L. Hernquist;D. Nelson;P. Torrey;D. Narayanan;Yin Li;O. Philcox;Valentina La Torre;Ana Maria Delgado;S. Ho;Sultan Hassan;B. Burkhart;D. Wadekar;N. Battaglia;Gabriella Contardo;G. Bryan
中科院分区：
文献类型：
--
作者：
F. Villaescusa-Navarro;D. Anglés-Alcázar;S. Genel;D. Spergel;Rachel S. Somerville;R. Davé;A. Pillepich;L. Hernquist;D. Nelson;P. Torrey;D. Narayanan;Yin Li;O. Philcox;Valentina La Torre;Ana Maria Delgado;S. Ho;Sultan Hassan;B. Burkhart;D. Wadekar;N. Battaglia;Gabriella Contardo;G. Bryan
我们提出了宇宙学和天体物理学与机器学习模拟（骆驼）项目。CAMELS是一套包含4233个宇宙学模拟，每个模拟体积为25h−1mp3； 2184个最先进的（磁电机）流体动力学模拟，使用AREPO和GIZMO代码运行，采用与IllustrisTNG和SIMBA模拟相同的重子子网格物理，以及2049个n体模拟。camel项目的目标是为不同的观测提供理论预测，作为宇宙学和天体物理学的一个功能，它是设计用于训练机器学习算法的最大的宇宙学（磁流体）动力学模拟套件。camel包含数千种不同的宇宙学和天体物理模型，通过改变Ω m， σ 8和控制恒星和活动星系核反馈的四个参数，在（400h−1Mpc）3的总体积内跟踪超过1000亿个粒子和流体元素的演化。我们详细描述了模拟，并描述了物质功率谱、宇宙恒星形成速率密度、星系恒星质量函数、晕重子分数和几个星系尺度关系所代表的大范围条件。我们表明，IllustrisTNG和SIMBA套件在全参数空间上产生了大致相似的星系特性分布，但在物质功率谱上的晕重子分数和重子效应有显著不同。这强调了边缘化重子效应的必要性，以便从宇宙学调查中提取最大数量的信息。我们使用几种机器学习应用来说明camel的独特潜力，包括非线性插值、参数估计、符号回归、生成对抗网络的数据生成、降维和异常检测。
We present the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project. CAMELS is a suite of 4233 cosmological simulations of 25h−1Mpc3 volume each: 2184 state-of-the-art (magneto)hydrodynamic simulations run with the AREPO and GIZMO codes, employing the same baryonic subgrid physics as the IllustrisTNG and SIMBA simulations, and 2049 N-body simulations. The goal of the CAMELS project is to provide theory predictions for different observables as a function of cosmology and astrophysics, and it is the largest suite of cosmological (magneto)hydrodynamic simulations designed to train machine-learning algorithms. CAMELS contains thousands of different cosmological and astrophysical models by way of varying Ω m , σ 8, and four parameters controlling stellar and active galactic nucleus feedback, following the evolution of more than 100 billion particles and fluid elements over a combined volume of (400h−1Mpc)3 . We describe the simulations in detail and characterize the large range of conditions represented in terms of the matter power spectrum, cosmic star formation rate density, galaxy stellar mass function, halo baryon fractions, and several galaxy scaling relations. We show that the IllustrisTNG and SIMBA suites produce roughly similar distributions of galaxy properties over the full parameter space but significantly different halo baryon fractions and baryonic effects on the matter power spectrum. This emphasizes the need for marginalizing over baryonic effects to extract the maximum amount of information from cosmological surveys. We illustrate the unique potential of CAMELS using several machine-learning applications, including nonlinear interpolation, parameter estimation, symbolic regression, data generation with Generative Adversarial Networks, dimensionality reduction, and anomaly detection.