评估神经网络在纯暗物质模拟中预测的星系形成历史
Evaluating the galaxy formation histories predicted by a neural network in pure dark matter simulations
AI总结：
本文评估了神经网络在纯暗物质模拟中预测星系形成历史的表现，发现模型能恢复总体统计量，但对低质量晕和低分辨率模拟存在显著偏差，并指出需考虑晕性质差异和分辨率影响。
摘要：
我们研究了一系列星系性质，这些性质是利用仅含暗物质的宇宙学模拟中的并合树和环境历史计算得到的，使用了一个半循环神经网络来产生自洽的星系演化预测，并利用基于类似预测的傅里叶变换对该模型进行了随机改进。我们将这些方法应用于IllustrisTNG模拟的仅含暗物质运行，以理解重子移除的影响，并应用于千兆秒差距体积的纯暗物质模拟Uchuu，以理解较低分辨率或晕性质替代度量的影响。我们发现，机器学习模型能够恢复由预测的恒星形成历史和恒星金属丰度历史导出的准确汇总统计量，以及相应的光谱学和测光结果。然而，该模型应用于暗物质模拟时的不准确性对于低质量和缓慢增长的暗晕来说是显著的。对于这些天体，由于缺乏恒星反馈，晕质量吸积率被夸大，但在低分辨率模拟中，由于缺少低质量前身天体，晕的形成可能受到严重限制。此外，较高质量晕的结构和环境的差异导致红色、淬灭星系的过度丰度。这些结果表明，在基于星系-晕联系的物理解释构建高保真模拟目录的机器学习模型方面取得了进展，但也说明需要考虑晕性质的差异和模拟分辨率的影响。
英文摘要：
We investigate a series of galaxy properties computed using the merger trees and environmental histories from dark matter only cosmological simulations, using a semi-recurrent neural network producing self-consistent predictions of galaxy evolution, and using stochastic improvements to this model based on similarly predicted Fourier Transforms. We apply these methods to the dark matter only runs of the IllustrisTNG simulations to understand the effects of baryon removal, and to the gigaparsec-volume pure dark matter simulation Uchuu, to understand the effects of the lower resolution or alternative metrics for halo properties. We find that the machine learning model recovers accurate summary statistics derived from the predicted star formation and stellar metallicity histories, and correspondent spectroscopy and photometry. However, the inaccuracies of the model's application to dark simulations are substantial for low mass and slowly growing haloes. For these objects, the halo mass accretion rate is exaggerated due to the lack of stellar feedback, yet the formation of the halo can be severely limited by the absence of low mass progenitors in a low resolution simulation. Furthermore, differences in the structure and environment of higher mass haloes results in an overabundance of red, quenched galaxies. These results signify progress towards a machine learning model which builds high fidelity mocks based on a physical interpretation of the galaxy-halo connection, yet they illustrate the need to account for differences in halo properties and the resolution of the simulation.
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。
