Quantifying uncertainties on fission fragment mass yields with mixture density networks
Quantifying uncertainties on fission fragment mass yields with mixture density networks
复制标题
用混合密度网络量化裂变碎片质量产量的不确定性
DOI：
10.1088/1361-6471/ab9f58
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
P. Talou
中科院分区：
文献类型：
--
作者：
A. Lovell;A. Mohan;P. Talou
概率机器学习技术既可以学习输入特征和感兴趣的输出数量之间的复杂关系，也可以考虑数据集中的随机性或不确定性。在这个初步的工作中，我们探索使用这样一个概率网络，混合密度网络（MDN），以再现裂变产率及其不确定性。我们研究$^{252}$Cf自发裂变的质量产率，探索收敛预测所需的训练样本的数量，不同程度的不确定性如何从训练集传播到MDN预测，以及产率的物理约束-例如归一化和对称性-如何被算法支持。最后，我们使用$^{235}$U上中子诱导裂变的能量依赖质量产率测试了MDN在训练集中样本之间进行插值和外推的能力。MDN提供了一种包括和预测不确定性的可靠方法，是补充稀疏核数据集的一个有前途的途径。
Probabilistic machine learning techniques can learn both complex relations between input features and output quantities of interest as well as take into account stochasticity or uncertainty within a data set. In this initial work, we explore the use of one such probabilistic network, the Mixture Density Network (MDN), to reproduce fission yields and their uncertainties. We study mass yields for the spontaneous fission of $^{252}$Cf, exploring the number of training samples needed for converged predictions, how different levels of uncertainty propagate from the training set to the MDN predictions, and how well physical constraints of the yields - such as normalization and symmetry - are upheld by the algorithm. Finally, we test the ability of the MDN to interpolate between and extrapolate beyond samples in the training set using energy-dependent mass yields for the neutron-induced fission on $^{235}$U. The MDN provides a reliable way to include and predict uncertainties and is a promising path forward for supplementing sparse sets of nuclear data.