Institute for Microelectronics, Technische Universität Wien, Gußhausstraße 27-29, 1040 Vienna, Austria.
Christian Doppler Laboratory for Single-Defect Spectroscopy in Semiconductor Devices at the Institute for Microelectronics, TU Wien, 1040 Vienna, Austria.
J Chem Phys. 2023 May 21;158(19). doi: 10.1063/5.0146753.
Silicon nitride (Si3N4) is an extensively used material in the automotive, aerospace, and semiconductor industries. However, its widespread use is in contrast to the scarce availability of reliable interatomic potentials that can be employed to study various aspects of this material on an atomistic scale, particularly its amorphous phase. In this work, we developed a machine learning interatomic potential, using an efficient active learning technique, combined with the Gaussian approximation potential (GAP) method. Our strategy is based on using an inexpensive empirical potential to generate an initial dataset of atomic configurations, for which energies and forces were recalculated with density functional theory (DFT); thereafter, a GAP was trained on these data and an iterative re-training algorithm was used to improve it by learning on-the-fly. When compared to DFT, our potential yielded a mean absolute error of 8 meV/atom in energy calculations for a variety of liquid and amorphous structures and a speed-up of molecular dynamics simulations by 3-4 orders of magnitude, while achieving a first-rate agreement with experimental results. Our potential is publicly available in an open-access repository.
氮化硅（Si3N4）是汽车、航空航天和半导体行业中广泛使用的材料。然而，与之形成鲜明对比的是，可靠的原子间势的稀缺，这些原子间势可用于在原子尺度上研究该材料的各个方面，特别是其非晶相。在这项工作中，我们开发了一种机器学习原子间势，使用了高效的主动学习技术，结合了高斯逼近势（GAP）方法。我们的策略基于使用廉价的经验势生成原子构型的初始数据集，其中能量和力是用密度泛函理论（DFT）重新计算的；此后，在这些数据上训练 GAP，并使用迭代再训练算法通过实时学习来改进它。与 DFT 相比，我们的势在计算各种液体和非晶结构的能量时产生了 8 meV/原子的平均绝对误差，并将分子动力学模拟的速度提高了 3-4 个数量级，同时与实验结果达成了一流的一致性。我们的势在一个开放获取的存储库中公开提供。
