从光锥数据中提取宇宙学信息:卷积神经网络与基于总结统计的方法的比较
Extracting Cosmological Information from Lightcone Data: A Comparison of CNNs and Summary-Statistic-Based Approaches
AI总结:
本文比较了CNN与基于总结统计的方法在提取光锥数据中宇宙学信息的效果,发现结合WST的全连接网络在参数约束上表现最佳,而CNN+2D方法在统计不确定性上表现最优。
摘要:
光锥观测是恒星巡天的自然数据格式,但其演化的几何结构破坏了标准卷积神经网络(CNN)所假设的平移对称性。特别是,将CNN应用于3D网格化的光锥数据会隐式地将视线方向视为平移不变,尽管编码了宇宙时间演化。我们提出了一种简单的替代方法(CNN+2D),将光锥分成红移切片,将每个切片投影到HEALPix球体上,并用2D CNN分析它们。使用AbacusSummit暗物质光锥模拟(0.3<z<0.8,40°×40°),我们比较了该方法与应用于不同总结统计的全连接网络(FC),包括球面谐波系数(a_{ℓm})、小波散射变换(WST)系数和角两点相关函数(2PCF),以及标准2PCF似然和Fisher预报。我们发现,多种统计量超越CNN可以实现竞争性的性能:FC网络结合a_{ℓm}和尤其WST显著优于基于2PCF的方法,FC+WST在不同宇宙学中产生最佳的参数约束。同时,对于具有多个现实的fiducial宇宙学,CNN+2D方法实现了最小的统计不确定性。这些结果表明,学习的特征和精心构造的总结统计量可以有效从光锥数据中提取宇宙学信息,为未来的调查如DESI、Euclid和CSST提供灵活且稳健的分析策略。
英文摘要:
Lightcone observations are the natural data format of galaxy surveys, but their evolving geometry breaks the translational symmetry assumed by standard convolutional neural networks (CNNs). In particular, applying CNNs to 3D gridded lightcone data implicitly treats the line-of-sight direction as translationally invariant, despite encoding cosmic time evolution. We propose a simple alternative (CNN+2D) that divides the lightcone into redshift slices, projects each onto a HEALPix sphere, and analyzes them with a 2D CNN. Using \texttt{AbacusSummit} halo lightcone mocks ($0.3<z<0.8$, $40^\circ\times40^\circ$), we compare this approach with fully connected networks (FC) applied to different summary statistics, including spherical harmonic coefficients ($a_{\ell m}$), wavelet scattering transform (WST) coefficients, and the angular two-point correlation function (2PCF), along with standard 2PCF likelihood and Fisher forecasts. We find that multiple statistics beyond CNNs can achieve competitive performance: FC networks combined with $a_{\ell m}$ and especially WST significantly outperform 2PCF-based methods, with FC+WST yielding the best overall parameter constraints across cosmologies. Meanwhile, for a fiducial cosmology with multiple realizations, the CNN+2D approach achieves the smallest statistical uncertainties. These results demonstrate that both learned features and carefully constructed summary statistics can effectively extract cosmological information from lightcone data, providing flexible and robust analysis strategies for upcoming surveys such as DESI, Euclid, and CSST.
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。