Machine Learning β-decay Half-lives and Their Application to r-Process Observables
Abstract
Accurately modeling β-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 β 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.
Related
- Optimising instrument concepts with Machine Learning: Application to CMB spectral distortion experiments
- Machine learning-based classification of type 1 active galactic nuclei
- Metaheuristic physics-informed extreme-learning machine for initial orbit determination of near-Earth asteroids from too-short arcs
- Data representation matters: Optimising machine learning for X-ray source classification by leveraging spatio-spectral information
- Parameter-Decoupled Superresolution with Airy-Disk-Informed Learning: Application to NGC 4486B
BibTeX
@misc{li2026machine,
title = {{Machine Learning $β$-decay Half-lives and Their Application to $r$-Process Observables}},
author = {Mengke Li and Flora Wang and Jonathan Engel and Matthew Mumpower and Rebecca Surman and Nicole Vassh},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2609.30408},
eprint = {2609.30408},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.30408},
}
RIS
TY - UNPB
TI - Machine Learning β-decay Half-lives and Their Application to r-Process Observables
AU - Mengke Li
AU - Flora Wang
AU - Jonathan Engel
AU - Matthew Mumpower
AU - Rebecca Surman
AU - Nicole Vassh
PY - 2026
DA - 2026/10/23
PB - arXiv
DO - 10.48550/arxiv.2609.30408
UR - https://arxiv.org/abs/2609.30408
AB - Accurately modeling β-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 β 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.
ER -