Extracting Cosmological Information from Lightcone Data: A Comparison of CNNs and Summary-Statistic-Based Approaches

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhiwei, Min, Xu, Xiao, Zhujun, Jiang, Liang, Xiao, Fenfen, Yin, Jiacheng, Ding, Haitao, Miao, Shupei, Chen, Qiufan, Lin, yang, Wang, Le, Zhang, XiaoDong, Li
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912985230868480
author Zhiwei, Min
Xu, Xiao
Zhujun, Jiang
Liang, Xiao
Fenfen, Yin
Jiacheng, Ding
Haitao, Miao
Shupei, Chen
Qiufan, Lin
yang, Wang
Le, Zhang
XiaoDong, Li
author_facet Zhiwei, Min
Xu, Xiao
Zhujun, Jiang
Liang, Xiao
Fenfen, Yin
Jiacheng, Ding
Haitao, Miao
Shupei, Chen
Qiufan, Lin
yang, Wang
Le, Zhang
XiaoDong, Li
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_26533
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Extracting Cosmological Information from Lightcone Data: A Comparison of CNNs and Summary-Statistic-Based Approaches
Zhiwei, Min
Xu, Xiao
Zhujun, Jiang
Liang, Xiao
Fenfen, Yin
Jiacheng, Ding
Haitao, Miao
Shupei, Chen
Qiufan, Lin
yang, Wang
Le, Zhang
XiaoDong, Li
Cosmology and Nongalactic Astrophysics
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.
title Extracting Cosmological Information from Lightcone Data: A Comparison of CNNs and Summary-Statistic-Based Approaches
topic Cosmology and Nongalactic Astrophysics
url https://arxiv.org/abs/2603.26533