Neural Network Reconstruction of Late-Time Cosmology and Null Tests
Preprint
Abstract
The prospect of nonparametric reconstructions of cosmological parameters from observational data sets has been a popular topic in the literature for a number of years. This has mainly taken the form of a technique based on Gaussian processes but this approach is exposed to several foundational issues ranging from overfitting to kernel consistency problems. In this work, we explore the possibility of using artificial neural networks (ANN) to reconstruct late-time expansion and large scale structure cosmological parameters. We first show how mock data can be used to design an optimal ANN for both parameters, which we then use with real data to infer their respective redshift profiles. We further consider cosmological null tests with the reconstructed data in order to confirm the validity of the concordance model of cosmology, in which we observe a mild deviation with cosmic growth data.Keywords
All Related Versions
This publication has 167 references indexed in Scilit:
- Constraints on Cosmographic Functions of Cosmic Chronometers Data Using Gaussian ProcessesBrazilian Journal of Physics, 2022
- A buyer’s guide to the Hubble constantThe Astronomy and Astrophysics Review, 2021
- Snowmass2021 - Letter of interest cosmology intertwined II: The hubble constant tensionAstroparticle Physics, 2021
- Snowmass2021 - Letter of interest cosmology intertwined I: Perspectives for the next decadeAstroparticle Physics, 2021
- A model of interacting dark matter and dark radiation for H0 and σ8 tensionsJournal of High Energy Physics, 2021
- Quantifying the
S
8
tension with the Redshift Space Distortion data setPhysics of the Dark Universe, 2021
- Interacting dark energy in the early 2020s: A promising solution to the
H
0
and cosmic shear tensionsPhysics of the Dark Universe, 2020
- Testing F(Q) gravity with redshift space distortionsPhysics of the Dark Universe, 2020
- Late time transitions in the quintessence field and the
H
0
tensionPhysics of the Dark Universe, 2019
- Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networksNeural Networks, 1990