From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning
复制标题
DOI：
10.1093/mnras/stab3088
复制
发表时间：
2021-10
期刊：
影响因子：
--
通讯作者：
Mauro Bernardini;R. Feldmann;D. Angl'es-Alc'azar;M. Boylan-Kolchin;J. Bullock;L. Mayer;J. Stadel
中科院分区：
文献类型：
--
作者：
Mauro Bernardini;R. Feldmann;D. Angl'es-Alc'azar;M. Boylan-Kolchin;J. Bullock;L. Mayer;J. Stadel
流体动力学模拟提供了一个强大的，但计算昂贵的方法来研究宇宙结构形成中暗物质和重子的相互作用。在这里，我们介绍了EM ulating B aryonic En Richment（EMBER）深度学习框架，以基于仅暗物质模拟来预测重子场，从而降低计算成本。EMBER包括两种网络架构，U-Net和Wasserstein生成对抗网络（WGANs），用于预测暗物质场的二维气体和H I密度。我们将条件WGAN设计为随机仿真器，以便可以从相同的暗物质输入中采样多个目标场。为了训练，我们结合联合收割机宇宙体积和放大流体动力学模拟从反馈在现实环境（火）项目，以代表一个大范围的规模。我们的fiducial WGAN模型在10%的准确度内再现了气体和H I功率谱，精确到10 kpc尺度。此外，我们调查的能力EMBER预测高分辨率重子场从低分辨率暗物质输入通过上采样技术。作为一个实际的应用，我们使用这种方法来模拟高分辨率的H I地图的暗物质模拟的一个100 Mpc /m2的宇宙学盒。𝐿暗物质晕的气体含量和由EMBER预测的H I柱密度分布与大体积宇宙学模拟和丰度匹配模型的结果吻合得很好。我们的方法提供了一个计算效率高的随机模拟器，用于用物理上一致的重子场地图来增强暗物质模拟。
Hydrodynamic simulations provide a powerful, but computationally expensive, approach to study the interplay of dark matter and baryons in cosmological structure formation. Here we introduce the EM ulating B aryonic E n R ichment (EMBER) Deep Learning framework to predict baryon fields based on dark-matter-only simulations thereby reducing computational cost. EMBER comprises two network architectures, U-Net and Wasserstein Generative Adversarial Networks (WGANs), to predict two-dimensional gas and H I densities from dark matter fields. We design the conditional WGANs as stochastic emulators, such that multiple target fields can be sampled from the same dark matter input. For training we combine cosmological volume and zoom-in hydrodynamical simulations from the Feedback in Realistic Environments (FIRE) project to represent a large range of scales. Our fiducial WGAN model reproduces the gas and H I power spectra within 10% accuracy down to ∼ 10 kpc scales. Furthermore, we investigate the capability of EMBER to predict high resolution baryon fields from low resolution dark matter inputs through upsampling techniques. As a practical application, we use this methodology to emulate high-resolution H I maps for a dark matter simulation of a 𝐿 = 100 Mpc / ℎ comoving cosmological box. The gas content of dark matter haloes and the H I column density distributions predicted by EMBER agree well with results of large volume cosmological simulations and abundance matching models. Our method provides a computationally efficient, stochastic emulator for augmenting dark matter only simulations with physically consistent maps of baryon fields.