arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07267astro-ph.CO
收藏

教神经网络生成快速Sunyaev Zel'dovich映射

Teaching neural networks to generate Fast Sunyaev Zel'dovich Maps

Leander Thiele, Francisco Villaescusa-Navarro, David N. Spergel, Dylan Nelson, Annalisa Pillepich

摘要:

热的Sunyaev-Zel'dovich(tSZ)效应和运动学的Sunyaev-Zel'dovich(kSZ)效应跟踪热宇宙中电子压力和动量的分布。这些观测值依赖于丰富的多尺度物理学,因此,模拟地图应该理想地基于捕获重子反馈效应的计算,例如冷却,恒星形成和其他复杂过程。在本文中,我们使用U-Net架构训练深度卷积神经网络,以~ 100 kpc分辨率从暗物质的三维分布映射到电子密度,动量和压力。这些网络是在TNG 300卷和来自IllustrisTNG项目的一组集群放大模拟的组合上训练的。神经网络能够比最先进的半分析模型更准确地再现模拟的功率谱、单点概率分布函数、双谱和互相关系数。我们的方法提供了一条路线,以捕获丰富的完整的宇宙学流体动力学模拟的星系形成与分析计算的速度。

英文摘要:

The thermal Sunyaev-Zel'dovich (tSZ) and the kinematic Sunyaev-Zel'dovich (kSZ) effects trace the distribution of electron pressure and momentum in the hot Universe. These observables depend on rich multi-scale physics, thus, simulated maps should ideally be based on calculations that capture baryonic feedback effects such as cooling, star formation, and other complex processes. In this paper, we train deep convolutional neural networks with a U-Net architecture to map from the three-dimensional distribution of dark matter to electron density, momentum and pressure at ~ 100 kpc resolution. These networks are trained on a combination of the TNG300 volume and a set of cluster zoom-in simulations from the IllustrisTNG project. The neural nets are able to reproduce the power spectrum, one-point probability distribution function, bispectrum, and cross-correlation coefficients of the simulations more accurately than the state-of-the-art semi-analytical models. Our approach offers a route to capture the richness of a full cosmological hydrodynamical simulation of galaxy formation with the speed of an analytical calculation.

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。

↑