Skip to content
Preprint

Machine Learning $\beta$-decay Half-lives and Their Application to $r$-Process Observables

Sep 2026 · 0 citations · 6 references
Physics

TL;DR

A data-driven approach to model $\beta$ decay that uses Mixture Density Networks trained on the latest experimental measurements to extrapolate the half-lives of neutron rich nuclei is introduced and the ranges of outcomes produced from the intrinsic uncertainty of a single model to those produced by multiple independent models trained on different training data sets are compared.

Abstract

Accurately modeling $\beta$-decay half-lives of highly neutron-rich nuclei is a critical challenge for understanding $r$-process nucleosynthesis and the resulting kilonova light curves. We introduce a data-driven approach to model $\beta$ decay that uses Mixture Density Networks (MDNs) trained on the latest experimental measurements to extrapolate the half-lives of neutron rich nuclei. Unlike standard deterministic regression, the MDN directly parameterizes the probability distribution of the half-lives, providing intrinsic (aleatoric) uncertainty. We contrast the intrinsic uncertainty of a single model with the range of models produced by using random variations of the input training data samples. While all models show excellent agreement with experimental data, we find that varying the training data sets produces a wide range of extrapolations, particularly along data-poor regions such as the $N=126$ isotonic chain. We then propagate a selection of model results into $r$-process network calculations to evaluate their impact on isotopic abundances. Finally, by coupling the resulting isotopic abundances with thermalization efficiencies, we translate the effective nuclear heating rates into bolometric light curves. We compare the ranges of outcomes produced from the intrinsic uncertainty of a single model to those produced by multiple independent models trained on different training data sets.

View source

Similar papers

#artificial intelligence Review Sep 2026

Learning Nuclear Structure with AI: Radii and Collectivity

Hold-out ensembles based on NuCLR (Nuclear Co-Learned Representations), a multi-task model of nuclear data, are developed to study charge radii and electric-quadrupole transition strengths and error bars estimate the expected prediction accuracy across the nuclear chart.

G. Giacalone, S. Trifinopoulos, Mike Williams · 0 citations
Oct 2026

"ISINN-32" Empirical predictions of $\alpha$-decay and spontaneous fission half-lives in the decay chains of elements 119 and 120

The competition between $\alpha$~decay and spontaneous fission in the decay chains of isotopes with $Z = 119$ and $120$ is investigated using empirical formulas. The $\alpha$-decay half-lives are calculated using the Viola--Seaborg semi-empirical formula, while the spontaneous fission half-lives are evaluated using a...

N. S. Moiseev, N. Antonenko, G. Adamian · 0 citations
Preprint Oct 2026

Inferring Nuclear Radial Parameters from Initial-State Information in Heavy-Ion Collisions Using Deep Neural Networks

The geometric structure of atomic nuclei plays an important role in shaping the initial conditions of high-energy nuclear collisions and the subsequent evolution of the quark--gluon plasma. In this work, we develop a multimodal deep-learning framework to infer the Woods--Saxon radius ($R_0$) and diffuseness parameter (...

Yang Liu, Yu Sha, Xiang Fan et al. · 0 citations
Preprint Sep 2026

Bottomonium suppression with a machine-learning-informed Debye mass

Motivated by recent progress in data-driven approaches, we introduce a machine-learning (ML)-informed Debye mass, extracted from lattice-informed inputs, exclusively in the complex-valued heavy-quark Kent State University (KSU) potential. The resulting complex potential is used to solve the real-time Schr\"odinger equa...

Ajaharul Islam, Shi-Bo Chen, Fu-Peng Li et al. · 0 citations
#machine learning Preprint Oct 2026

$\sigma$Transfer: Uncertainty Transfer from Small to Large Networks under $\mu\mathrm{P}$

Reliable predictive uncertainty in Laplace approximations depends critically on the prior precision, yet selecting it requires a posterior sweep that is prohibitively expensive for neural networks with billions of parameters. Under the Maximal Update Parametrization ($\mu\mathrm{P}$), we derive a rescaling of the prior...

Richard Bergna, Fernando Ruiz Mazo, Nicolò Felicioni et al. · 0 citations
#machine learning Preprint Sep 2026

Fast Learning Rates for Physics-Informed Kernel Methods

This work considers the setting where $D$ is a linear differential operator and analyzes a physics-informed kernel estimator combining value observations and differential observations to derive physically consistent rates in a stronger norm that jointly controls the errors in $\hat u$ and $D\hat u$.

Luc Brogat-Motte, Joachim Bona-Pellissier, G. Meanti et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.