BBNet: accurate neural network emulator for primordial light element abundances

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Fan, Diao, Hang, Li, Bohua, Meyers, Joel, Shapiro, Paul R.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915681572749312
author Zhang, Fan
Diao, Hang
Li, Bohua
Meyers, Joel
Shapiro, Paul R.
author_facet Zhang, Fan
Diao, Hang
Li, Bohua
Meyers, Joel
Shapiro, Paul R.
contents Big-Bang Nucleosynthesis (BBN) predictions of primordial light-element abundances offer a powerful probe of early-Universe physics. However, high-accuracy numerical BBN calculations have become a major computational bottleneck for large-scale cosmological inferences due to the complex nuclear network. Here we present BBNet, a fast and accurate deep learning emulator for primordial abundances. The training data are generated by full numerical calculations using two public BBN codes, PArthENoPE and AlterBBN, modified to accommodate extended cosmologies that include dark radiation and a stiff equation of state. The network employs a residual multi-head architecture to capture convoluted physical relationships. BBNet produces primordial helium-4 and deuterium abundances with negligible errors in milliseconds per sample, achieving a speed-up of up to $10^4$ times relative to first-principles solvers while remaining unbiased over wide parameter ranges. Therefore, our emulator can supersede traditional simplified numerical prescriptions that compromise accuracy for speed. Based on extensive assessments of its performance, we conclude that BBNet is an optimal solution to the theoretical prediction of primordial element abundances. It will serve as a reliable tool for precision cosmology and new-physics searches.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15266
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BBNet: accurate neural network emulator for primordial light element abundances
Zhang, Fan
Diao, Hang
Li, Bohua
Meyers, Joel
Shapiro, Paul R.
Cosmology and Nongalactic Astrophysics
High Energy Astrophysical Phenomena
General Relativity and Quantum Cosmology
High Energy Physics - Phenomenology
Big-Bang Nucleosynthesis (BBN) predictions of primordial light-element abundances offer a powerful probe of early-Universe physics. However, high-accuracy numerical BBN calculations have become a major computational bottleneck for large-scale cosmological inferences due to the complex nuclear network. Here we present BBNet, a fast and accurate deep learning emulator for primordial abundances. The training data are generated by full numerical calculations using two public BBN codes, PArthENoPE and AlterBBN, modified to accommodate extended cosmologies that include dark radiation and a stiff equation of state. The network employs a residual multi-head architecture to capture convoluted physical relationships. BBNet produces primordial helium-4 and deuterium abundances with negligible errors in milliseconds per sample, achieving a speed-up of up to $10^4$ times relative to first-principles solvers while remaining unbiased over wide parameter ranges. Therefore, our emulator can supersede traditional simplified numerical prescriptions that compromise accuracy for speed. Based on extensive assessments of its performance, we conclude that BBNet is an optimal solution to the theoretical prediction of primordial element abundances. It will serve as a reliable tool for precision cosmology and new-physics searches.
title BBNet: accurate neural network emulator for primordial light element abundances
topic Cosmology and Nongalactic Astrophysics
High Energy Astrophysical Phenomena
General Relativity and Quantum Cosmology
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2512.15266