Deep learning simulations of the microwave sky
Deep learning simulations of the microwave sky
复制标题
DOI：
10.1103/physrevd.104.123521
复制
发表时间：
2021-05
影响因子：
5
通讯作者：
Dongwon Han;N. Sehgal;F. Villaescusa-Navarro
中科院分区：
文献类型：
--
作者：
Dongwon Han;N. Sehgal;F. Villaescusa-Navarro
我们展示了 500 个高分辨率、全天空毫米波深度学习 (DL) 模拟，其中包括透镜 CMB 地图和相关的前景组件。我们发现这些 MillimeterDL 模拟可以重现与输入训练模拟相匹配的各种非高斯汇总统计数据，同时仅进行优化以匹配功率谱。我们在这项工作中开发的程序能够从单个昂贵的全天空模拟中批量生产独立的全天空实现，而后者通常无法提供足够的训练数据。我们还规避了高分辨率深度学习模拟的一个常见限制，即它们通常由于内存或 GPU 问题而局限于较小的天空区域；我们通过开发一种“缝合”程序来做到这一点，该程序可以忠实地恢复全天空地图的高阶统计数据，而不会出现不连续或重复的特征。此外，由于我们的网络以全天透镜收敛图作为输入，因此原则上它可以从任何大规模结构（LSS）模拟中获取全天透镜收敛图，并生成相应的透镜CMB和毫米波长的相关前景分量；这在当前结合 CMB 和 LSS 调查结果的时代尤其有用，因为这需要一组通用的模拟。
We present 500 high-resolution, full-sky millimeter-wave Deep Learning (DL) simulations that include lensed CMB maps and correlated foreground components. We find that these MillimeterDL simulations can reproduce a wide range of non-Gaussian summary statistics matching the input training simulations, while only being optimized to match the power spectra. The procedure we develop in this work enables the capability to mass produce independent full-sky realizations from a single expensive full-sky simulation, when ordinarily the latter would not provide enough training data. We also circumvent a common limitation of high-resolution DL simulations that they be confined to small sky areas, often due to memory or GPU issues; we do this by developing a"stitching"procedure that can faithfully recover the high-order statistics of a full-sky map without discontinuities or repeated features. In addition, since our network takes as input a full-sky lensing convergence map, it can in principle take a full-sky lensing convergence map from any large-scale structure (LSS) simulation and generate the corresponding lensed CMB and correlated foreground components at millimeter wavelengths; this is especially useful in the current era of combining results from both CMB and LSS surveys, which require a common set of simulations.