arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.17136nucl-thnucl-exphysics.data-an
收藏

用机器学习预测β衰变能量

Predicting Beta Decay Energy with Machine Learning

Jose M. Munoz, Serkan Akkoyun, Zayda P. Reyes, Leonardo A. Pachon

摘要:

$Q_β$代表了表征不稳定核的最重要因素之一,因为它可以更好地理解核的行为和重原子的起源。最近,机器学习方法已被证明是一种强大的工具,可以提高预测各种原子性质的准确性,例如能量,原子电荷,体积等。尽管如此,这些方法通常被用作黑盒,不允许解开分析中的现象的见解。在这里,通过机器学习模型的集合,实验数据上的$β$ -衰变能量的最先进的精度被超越。为消除黑箱问题而实施的可解释性工具允许将不确定性和原子序数确定为预测$Q_β$能量的最相关特征。此外,物理信息特征的加入提高了模型的鲁棒性,提高了原子核结构理论模型的重要特征。

英文摘要:

$Q_β$ 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, 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 uncertainty and atomic number as the most relevant characteristics to predict $Q_β$ energies. Furthermore, physics-informed feature addition improved models' robustness and raised vital characteristics of theoretical models of the nuclear structure.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑