Predictions of nuclear $\beta$-decay half-lives with machine learning and their impacts on $r$ process

TL;DR

This paper introduces a machine learning approach using Bayesian neural networks to predict nuclear $eta$-decay half-lives accurately, incorporating known physics and learning unknown effects, significantly improving predictions for astrophysical $r$-process modeling.

Contribution

The study presents a novel Bayesian neural network method that explicitly embeds known physics and learns unknown effects to predict $eta$-decay half-lives with high accuracy.

Findings

High-accuracy reproduction of experimental half-lives

Provides reliable uncertainty estimates for predictions

Enhances $r$-process nucleosynthesis simulations

Abstract

Nuclear $\beta$ decay is a key process to understand the origin of heavy elements in the universe, while the accuracy is far from satisfactory for the predictions of $\beta$-decay half-lives by nuclear models up to date. In this letter, we pave a novel way to accurately predict $\beta$-decay half-lives with the machine-learning based on the Bayesian neural network, in which the known physics has been explicitly embedded, including the ones described by the Fermi theory of $\beta$ decay, and the dependence of half-lives on pairing correlations and decay energies. The other potential physics, which is not clear or even missing in nuclear models nowadays, will be learned by the Bayesian neural network. The results well reproduce the experimental data with a very high accuracy and further provide reasonable uncertainty evaluations in half-life predictions. These accurate predictions for half-lives with uncertainties are essential for the $r$-process simulations.