论文标题
核质量的物理解释的机器学习
Physically Interpretable Machine Learning for nuclear masses
论文作者
论文摘要
我们提出了一种新的方法，可以直接基于受相关物理学约束的概率神经网络建模原子核的基态质量。我们的物理解释的机器学习（PIML）方法还通过使用具有物理动机的特征空间来结合物理知识，此外还可以实现损失功能的惩罚。我们在随机的$ \ sim $ 20 \％的原子量评估（AME）上训练我们的PIML模型，并预测其余的$ \ sim $ 80 \％。我们方法的成功由前所未有的$σ_\ textrm {rms} \ sim186 $ kev匹配到训练集的数据，$σ_\ textrm {rms} \ sim316 $ kev均以$ z \ geq 20 $ 20 $。我们证明我们的一般方法可以使用特征重要性来解释。
We present a novel approach to modeling the ground state mass of atomic nuclei based directly on a probabilistic neural network constrained by relevant physics. Our Physically Interpretable Machine Learning (PIML) approach incorporates knowledge of physics by using a physically motivated feature space in addition to a soft physics constraint that is implemented as a penalty to the loss function. We train our PIML model on a random set of $\sim$20\% of the Atomic Mass Evaluation (AME) and predict the remaining $\sim$80\%. The success of our methodology is exhibited by the unprecedented $σ_\textrm{RMS}\sim186$ keV match to data for the training set and $σ_\textrm{RMS}\sim316$ keV for the entire AME with $Z \geq 20$. We show that our general methodology can be interpreted using feature importance.
