Machine learning study on nuclear α decays

초록

The regression process of machine learning is applied to investigate the pattern of alpha decay half-lives of heavy nuclei. By making use of the available experimental data for 164 nuclides, we scrutinize the predictive power of machine learning in the study of nuclear alpha decays within two approaches. In Model (I), we trained neural networks to experimental data of the half-lives of nuclear alpha decays directly while, in Model (II), they are trained to the gap between the experimental data and the predictions of the Viola-Seaborg formula as a theoretical model. The purpose of Model (I) was to verify the applicability of machine learning to nuclear alpha decays, and the motivation of Model (II) was to apply the technique to estimate the uncertainties in the predictions of theoretical models. Out results show that room exists for improving the predictions of empirical models by using machine learning techniques. We also present predictions on unmeasured nuclear alpha decays. © 2021 The Korean Physical Society. All rights reserved.

키워드