Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
Predicting Localized Primordial Star Formation with Deep Convolutional Neural Networks
复制标题
用深度卷积神经网络预测局部原始恒星形成
DOI：
10.3847/1538-4365/abfa17
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
M. Norman
中科院分区：
文献类型：
--
作者：
Azton I. Wells;M. Norman
在第一批星系的流体力学宇宙学模拟中，我们研究了3D深卷积神经网络作为原始恒星形成和反馈效应的快速替代模型的应用。在这里，我们提出了代理模型来预测局域原始星的形成；反馈模型将在后续的论文中给出。恒星形成预测模型由两个子模型组成：第一个是3D体积分类器，它预测哪些(10个循环KPC)3个体积将包含恒星形成，然后是一个基于3D初始的U-Net体素分割模型，它预测哪些体素将形成原始恒星。我们发现，组合模型以高技能预测原始恒星形成体积，F1>；0.995和真实技能得分(Tss)>；0.994。恒星的形成在体积内定位到≲53体素(∼1.6共同移动kpc3)与F1>；0.399和tss>；0.857。应用于低空间分辨率的模拟，该模型预测了恒星形成区域与已分解的全物理模拟中的位置相同、红移相似的区域，这些模拟明确地模拟了原始恒星的形成和反馈。当应用于较低质量分辨率的模拟时，我们发现，由于较低质量分辨率导致的结构形成延迟，该模型在较晚的红移时预测了恒星形成区域。我们的模型预测了原始恒星的形成，而不是寻找晕，因此它将在空间分辨率不高的模拟中有用，因为它无法解析原始恒星形成晕。据我们所知，这是第一个可以预测与高分辨率宇宙模拟相匹配的原始恒星形成区域的模型。
We investigate applying 3D deep convolutional neural networks as fast surrogate models of the formation and feedback effects of primordial stars in hydrodynamic cosmological simulations of the first galaxies. Here, we present the surrogate model to predict localized primordial star formation; the feedback model will be presented in a subsequent paper. The star formation prediction model consists of two submodels: the first is a 3D volume classifier that predicts which (10 comoving kpc)3 volumes will host star formation, followed by a 3D Inception-based U-net voxel segmentation model that predicts which voxels will form primordial stars. We find that the combined model predicts primordial star-forming volumes with high skill, with F 1 > 0.995 and true skill score (TSS) >0.994. The star formation is localized within the volume to ≲53 voxels (∼1.6 comoving kpc3) with F 1 > 0.399 and TSS >0.857. Applied to simulations with low spatial resolution, the model predicts star-forming regions in the same locations and at similar redshifts as sites in resolved full-physics simulations that explicitly model primordial star formation and feedback. When applied to simulations with lower mass resolution, we find that the model predicts star-forming regions at later redshift due to delayed structure formation resulting from lower mass resolution. Our model predicts primordial star formation without halo finding, so it will be useful in spatially under-resolved simulations that cannot resolve primordial star-forming halos. To our knowledge, this is the first model that can predict primordial star-forming regions that match highly resolved cosmological simulations.
影响因子：
64.8
作者：
M. Vogelsberger;S. Genel;V. Springel;P. Torrey;D. Sijacki;Da Xu;G. Snyder;Simeon Bird;D. Nelson;Lars Hernquist Mit;HarvardCfA;Hits;I. Cambridge;Stsci;Ias Princeton
通讯作者：
M. Vogelsberger;S. Genel;V. Springel;P. Torrey;D. Sijacki;Da Xu;G. Snyder;Simeon Bird;D. Nelson;Lars Hernquist Mit;HarvardCfA;Hits;I. Cambridge;Stsci;Ias Princeton
影响因子：
4.8
作者：
Coral Wheeler;P. Hopkins;A. Pace;S. Garrison-Kimmel;M. Boylan-Kolchin;A. Wetzel;J. Bullock;D. Keres
通讯作者：
Coral Wheeler;P. Hopkins;A. Pace;S. Garrison-Kimmel;M. Boylan-Kolchin;A. Wetzel;J. Bullock;D. Keres