dc.contributor.author | Serkan Akkoyun | |
dc.date.accessioned | 2024-02-28T13:53:08Z | |
dc.date.available | 2024-02-28T13:53:08Z | |
dc.date.issued | 2023/3/15 | tr |
dc.identifier.uri | https://hdl.handle.net/20.500.12418/14438 | |
dc.description.abstract | Q β represents one of the most important factors characterizing unstable nuclei, as it can lead to a better understanding of nuclei behavior and the origin of heavy atoms. Recently, machine learning methods have been shown to be a powerful tool to increase accuracy in the prediction of diverse atomic properties such as energies, atomic charges, and volumes, among others. Nonetheless, these methods are often used as a black box not allowing unraveling insights into the phenomena under analysis. Here, the state-of-the-art precision of the β-decay energy on experimental data is outperformed by means of an ensemble of machine-learning models. The explainability tools implemented to eliminate the black box concern allowed to identify proton and neutron numbers as the most relevant characteristics to predict Q β energies. Furthermore, a physics-informed feature addition improved models' robustness and … | tr |
dc.rights | info:eu-repo/semantics/openAccess | tr |
dc.title | Predicting -decay energy with machine learning | tr |
dc.type | article | tr |
dc.contributor.department | Fen Fakültesi | tr |
dc.relation.publicationcategory | Uluslararası Hakemli Dergide Makale - Kurum Öğretim Elemanı | tr |