Constraining nuclear mass models using r-process observables with multi-objective optimization
M. Li, M. Mumpower, N. Vassh, W. S. Porter, R. Surman
Published PRRL (2025)
Predicting nuclear masses is a longstanding challenge. One path forward is machine learning (ML) which trains on experimental data, but can suffer large errors when extrapolating toward neutron-rich species. In nature, such masses shape observables for the rapid neutron capture process (r-process), which in principle could inform ML models. Here we introduce a multi-objective optimization approach using the Pareto Front algorithm. We show that this technique, capable of identifying models which generate r-process abundances aligning with both Solar and stellar data, is a promising method to select ML models with reliable extrapolation power.
@article{Li2025Constraining,
title = {Constraining nuclear mass models using {$r$}-process observables with multiobjective optimization},
volume = {7},
issn = {2643-1564},
doi = {10.1103/3x9p-64w7},
number = {3},
journal = {Physical Review Research},
publisher = {American Physical Society (APS)},
author = {Li, Mengke and Mumpower, Matthew and Vassh, Nicole and Porter, William Samuel and Surman, Rebecca},
year = {2025},
month = {Sept},
pages = {L032057},
}
