Deep Learning Based Recalibration of SDSS and DESI BAO Alleviates Hubble and Clustering Tensions

TL;DR

This paper uses deep learning to recalibrate BAO data from SDSS and DESI, reducing tensions in Hubble constant and clustering measurements without relying on specific cosmological models.

Contribution

It introduces a model-independent deep learning approach to recalibrate BAO data, leading to significant tension alleviation in key cosmological parameters.

Findings

Reduces Hubble tension ($H_0$) significantly.

Decreases clustering tension ($S_8$) notably.

Indicates potential for further data-driven cosmological analyses.

Abstract

Conventional calibration of Baryon Acoustic Oscillations (BAO) data relies on estimation of the sound horizon at drag epoch $r_d$ from early universe observations by assuming a cosmological model. We present a recalibration of two independent BAO datasets, SDSS and DESI, by employing deep learning techniques for model-independent estimation of $r_d$, and explore the impacts on $\Lambda$CDM cosmological parameters. Significant reductions in both Hubble ($H_0$) and clustering ($S_8$) tensions are observed for both the recalibrated datasets. Moderate shifts in some other parameters hint towards further exploration of such data-driven approaches.