追溯宇宙起源：利用机器学习从再电离时期观测中重构原初密度场
Tracing the Cosmic Origins: Machine Learning Reconstruction of the Primordial Density Field from EoR Observations
浏览论文内容
中文总结 AI 辅助
该研究利用三维U-Net从模拟的21厘米和CO线强度图重构原初密度场，结合两种示踪物可提升参数约束精度，为未来宇宙学观测提供了有效方法。
中文摘要 AI 辅助
从晚期示踪物重构宇宙初始条件，可解锁被非线性结构形成和天体物理学过程掩盖的宇宙学信息。我们利用LIMFAST生成的z~8处模拟21厘米线和CO(1-0)线强度图，重构z~300处的初始密度场。采用三维U-Net模型完成初始条件重构，并评估其对宇宙学参数约束的影响。这两种示踪物探测互补环境：21厘米发射迹踪星系际介质中中性低密度区域，CO则迹踪过密的恒星形成区域。为模拟真实观测，我们对类SKA1-Low和COMAP-ERA巡天的仪器效应进行建模，包括有限角分辨率和热噪声。我们通过重构与真实初始密度场的互相关系数|C(k)|评估重构性能：无噪声情况下，结合两种示踪物可在所有电离态中实现最精确的恢复，当k≤0.75 Mpc⁻¹时|C(k)|≥0.90；加入观测效应后，小尺度信息有所退化，但结合示踪物仍可在k≤0.3 Mpc⁻¹时实现|C(k)|≥0.70。为量化信息增益，我们在重构前后对功率谱摘要进行基于模拟的宇宙学参数推断：无论无噪声还是有噪声场景，重构均收紧了参数约束，σ₈和nₛ的不确定性提升约2倍，其他参数也有更小但一致的增益，这一点通过对观测集合的Kullback-Leibler散度诊断进一步得到证实。这些结果表明，未来21厘米和CO巡天的联合分析结合此类重构，可部分恢复原本无法获取的宇宙学信息。
英文摘要
Reconstructing the initial conditions of the Universe from late-time tracers would unlock cosmological information buried by non-linear structure formation and astrophysics. We reconstruct the initial density field at $z\sim300$ from simulated 21-cm and CO(1-0) line-intensity maps at $z\sim8$ generated with LIMFAST. Using a three-dimensional U-Net, we reconstruct the initial conditions and evaluate its impact on cosmological parameter constraints. The two tracers probe complementary environments: 21-cm emission traces neutral, low-density regions of the intergalactic medium, while CO traces overdense, star-forming regions. To emulate realistic observations, we model instrumental effects for SKA1-Low- and COMAP-ERA-like surveys, including finite angular resolution and thermal noise. We assess reconstruction performance through the cross-correlation coefficient between reconstructed and true initial density fields, $|C(k)|$. In the noiseless case, combining both tracers delivers the most accurate recovery across ionisation states, with $|C(k)| \gtrsim$ 0.90 for $k \lesssim$ 0.75 Mpc$^{-1}$. With observational effects, small-scale information is degraded, but combining tracers still achieves $|C(k)| \gtrsim$ 0.70 for $k \lesssim$ 0.3 Mpc$^{-1}$. To quantify information gain, we perform simulation-based inference of cosmological parameters from power-spectrum summaries before and after reconstruction. In both noiseless and noisy settings, reconstruction tightens parameter constraints: uncertainties on $σ_8$ and $n_{\rm s}$ improve by $\sim2\times$, with smaller but consistent gains for other parameters. This is further confirmed using Kullback-Leibler divergence diagnostics for an ensemble of observations. These results indicate that joint analysis of future 21-cm and CO surveys, combined with such reconstruction, can partially recover otherwise inaccessible cosmological information.
发表机构
- Van Swinderen Institute, University of Groningen（格罗宁根大学范斯温德伦研究所）
- Northwestern University（西北大学）
- Jet Propulsion Laboratory, California Institute of Technology（加州理工学院喷气推进实验室）
- California Institute of Technology（加州理工学院）
- University of California, Santa Cruz（加州大学圣克鲁兹分校）
机构由 AI 辅助整理，请以论文原文为准。
