Machine learning of the quantitative relationship between local environment descriptors and the potential energy surface of a system of atoms has emerged as a new frontier in the development of interatomic potentials (IAPs). Here, we present a comprehensive evaluation of machine learning IAPs (ML-IAPs) based on four local environment descriptors-atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the spectral neighbor analysis potential (SNAP) bispectrum components, and moment tensors-using a diverse data set generated using high-throughput density functional theory (DFT) calculations. The data set comprising bcc (Li, Mo) and fcc (Cu, Ni) metals and diamond group IV semiconductors (Si, Ge) is chosen to span a range of crystal structures and bonding. All descriptors studied show excellent performance in predicting energies and forces far surpassing that of classical IAPs, as well as predicting properties such as elastic constants and phonon dispersion curves. We observe a general trade-off between accuracy and the degrees of freedom of each model and, consequently, computational cost. We will discuss these trade-offs in the context of model selection for molecular dynamics and other applications.

中文翻译：

---

机器学习原子间电势的性能和成本评估。

机器学习的局部环境描述符和原子系统的势能面之间的定量关系已成为原子间势（IAP）发展的新领域。在这里，我们基于四个局部环境描述符-以原子为中心的对称函数（ACSF），原子位置的平滑重叠（SOAP），光谱邻居分析潜力（SNAP）双谱，对机器学习IAP（ML-IAP）进行了全面评估组件和力矩张量-使用通过高通量密度泛函理论（DFT）计算生成的多样化数据集。选择包含bcc（Li，Mo）和fcc（Cu，Ni）金属以及第IV金刚石组半导体（Si，Ge）的数据集以跨越一定范围的晶体结构和键合。所有研究的描述子在预测能量和力方面都表现出卓越的性能，远远超过了经典IAP，并且还预测了诸如弹性常数和声子色散曲线之类的特性。我们观察到了每个模型的准确性和自由度之间的一般权衡，因此也需要计算成本。我们将在分子动力学和其他应用的模型选择的背景下讨论这些权衡。