论文标题
在热通量正规化下构建机器学习的原子间潜力及其在银色葡萄糖生成层的功率谱分析中的应用
Construction of Machine-Learning Interatomic Potential Under Heat Flux Regularization and Its Application to Power Spectrum Analysis for Silver Chalcogenides
论文作者
论文摘要
我们提出了一种数据驱动的方法,用于构建在正规化下训练的机器学习间的原子间电位(MLIP),目的是避免非物理热通量。具体而言,我们将热通量的正则化项引入了要最小化的MLIP的成本函数。由于使用MLIP和正则化的热通量处理可以分解为元素贡献或在频率空间中进行的,因此该方法有望可用于研究从绿色kubo公式获得的热导率的起源。但是,需要适当设置正则化的强度,因为它不仅可以减少非物理部分,还可以减少固有的热通量。为此,我们研究了构建MLIP的条件,这些条件可以重现与Ag $ _2 $ SE经验的原子间潜能相关的热通量的功率光谱,该原子间潜能由成对功能组成,不包含非物理热通量。可以从正则化项的大小的变化以及总势能,原子力和病毒应力相对于强度而没有参考频谱数据的病毒应力来估算适当的强度。作为一个应用程序示例,我们探讨了基于热通量正则化的超级离子和非维生素导电阶段之间的功率光谱差异,以训练Ag $ _2 $ s的第一原理计算数据的MLIP。此外,我们的结果表明,进行正则化的训练可以改善MLIP的鲁棒性以及非物理热通量的减少。
We propose a data-driven approach for constructing machine-learning interatomic potentials (MLIPs) trained under a regularization with the aim of avoiding nonphysical heat flux. Specifically, we introduce a regularization term for the heat flux into the cost function of MLIPs to be minimized. Since the treatment of heat flux using MLIPs with regularization can be decomposed into elemental contributions or conducted in frequency space, this approach is expected to be useful for investigating the origin of thermal conductivity obtained from the Green-Kubo formula. However, the strength of regularization needs to be appropriately set because it may reduce not only the nonphysical part but also the intrinsic heat flux one. To this end, we investigated the conditions for constructing MLIPs that can reproduce the power spectra of heat flux associated with the empirical interatomic potential of Ag$_2$Se, which consists of pairwise functions and do not contain a nonphysical heat flux. The appropriate strength could be estimated from the variation of the magnitude of regularization term as well as root mean square errors for total potential energy, atomic force, and virial stress with respect to the strengths, without reference spectrum data. As an application example, we explored the differences in power spectra between superionic and nonsuperionic conducting phases based on the heat flux regularization to MLIPs trained with the first-principles calculation data of Ag$_2$S. Furthermore, our results demonstrate that training with the regularization improves the robustness of MLIPs as well as the reduction of the nonphysical heat flux.