The development of reliable and flexible machine learning based interatomic potentials (ML-IPs) is becoming increasingly important in studying the physical properties of complex condensed matter systems. Besides the structure descriptor model for total energy decomposition, the trial-and-error approach used in the design of the training dataset makes the ML-IP hardly improvable and reliable for modeling materials with chemical bond hierarchy. In this work, a dual adaptive sampling (DAS) method with an on the fly ambiguity threshold was developed to automatically generate an effective training dataset covering a wide temperature range or a wide spectrum of thermodynamic conditions. The DAS method consists of an inner loop for exploring the local configuration space and an outer loop for covering a wide temperature range. We validated the developed DAS method by simulating thermal transport of complex materials. The simulation results show that even with a substantially small dataset, our approach not only accurately reproduces the energies and forces but also predicts reliably effective high-order force constants to at least fourth order. The lattice thermal conductivity and its temperature dependence were evaluated using the Green-Kubo simulations with ML-IP for $\mathrm{Co}{\mathrm{Sb}}_3$ with up to third-order phonon scattering, and those for ${\mathrm{Mg}}_3{\mathrm{Sb}}_2$ with up to fourth-order phonon scattering, and all show good agreements with experiments. Our work provides an avenue to effectively construct a training dataset for ML-IP of complex materials with chemical bond hierarchy.

中文翻译：

---

双自适应采样和机器学习原子间势，用于模拟具有化学键层次的材料

可靠且灵活的基于机器学习的原子间势 (ML-IP) 的开发在研究复杂凝聚态系统的物理特性方面变得越来越重要。除了用于总能量分解的结构描述符模型外，在训练数据集设计中使用的试错法使得 ML-IP 难以改进，并且对于具有化学键层次结构的材料建模是可靠的。在这项工作中，开发了一种具有动态模糊阈值的双自适应采样 (DAS) 方法，以自动生成覆盖宽温度范围或宽范围热力学条件的有效训练数据集。DAS 方法由用于探索局部配置空间的内循环和用于覆盖较宽温度范围的外循环组成。我们通过模拟复杂材料的热传输验证了开发的 DAS 方法。模拟结果表明，即使数据集非常小，我们的方法不仅可以准确地再现能量和力，而且还可以可靠地预测至少四阶的有效高阶力常数。使用带有 ML-IP 的 Green-Kubo 模拟评估晶格热导率及其温度依赖性$\mathrm{公司}{锑}_3$ 具有高达三阶声子散射，以及那些 ${镁}_3{锑}_2$具有高达四阶声子散射，并且都显示出与实验良好的一致性。我们的工作为有效构建具有化学键层次的复杂材料的 ML-IP 训练数据集提供了途径。