Saved in:
Bibliographic Details
Main Authors: Röver, Lennart, Schäfer, Björn Malte, Plehn, Tilman
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.13899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929285816647680
author Röver, Lennart
Schäfer, Björn Malte
Plehn, Tilman
author_facet Röver, Lennart
Schäfer, Björn Malte
Plehn, Tilman
contents The Hubble function characterizes a given Friedmann-Robertson-Walker spacetime and can be related to the densities of the cosmological fluids and their equations of state. We show how physics-informed neural networks (PINNs) emulate this dynamical system and provide fast predictions of the luminosity distance for a given choice of densities and equations of state, as needed for the analysis of supernova data. We use this emulator to perform a model-independent and parameter-free reconstruction of the Hubble function on the basis of supernova data. As part of this study, we develop and validate an uncertainty treatment for PINNs using a heteroscedastic loss and repulsive ensembles.
format Preprint
id arxiv_https___arxiv_org_abs_2403_13899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PINNferring the Hubble Function with Uncertainties
Röver, Lennart
Schäfer, Björn Malte
Plehn, Tilman
Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
High Energy Physics - Phenomenology
The Hubble function characterizes a given Friedmann-Robertson-Walker spacetime and can be related to the densities of the cosmological fluids and their equations of state. We show how physics-informed neural networks (PINNs) emulate this dynamical system and provide fast predictions of the luminosity distance for a given choice of densities and equations of state, as needed for the analysis of supernova data. We use this emulator to perform a model-independent and parameter-free reconstruction of the Hubble function on the basis of supernova data. As part of this study, we develop and validate an uncertainty treatment for PINNs using a heteroscedastic loss and repulsive ensembles.
title PINNferring the Hubble Function with Uncertainties
topic Cosmology and Nongalactic Astrophysics
Instrumentation and Methods for Astrophysics
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2403.13899