Machine learning (ML) based interatomic potentials are emerging tools for material simulations, but require a trade-off between accuracy and speed. Here, we show how one can use one ML potential model to train another: we use an accurate, but more computationally expensive model to generate reference data (locations and labels) for a series of much faster potentials. Without the need for quantum-mechanical reference computations at the secondary stage, extensive reference datasets can be easily generated, and we find that this improves the quality of fast potentials with less flexible functional forms. We apply the technique to disordered silicon, including a simulation of vitrification and polycrystalline grain formation under pressure with a system size of a million atoms. Our work provides conceptual insight into the ML of interatomic potential models and suggests a route toward accelerated simulations of condensed-phase systems. (C)2022 Author(s). All article content, except where otherwise noted, is licensed under a Creative Commons Attribution (CC BY) license(http://creativecommons.org/licenses/by/4.0/)
展开▼
机译：基于机器学习 （ML） 的原子间势是用于材料模拟的新兴工具，但需要在精度和速度之间进行权衡。在这里，我们展示了如何使用一个 ML 电位模型来训练另一个 ML 电位模型：我们使用一个准确但计算成本更高的模型来生成一系列更快的电位的参考数据（位置和标签）。在二级阶段不需要量子力学参考计算，可以很容易地生成广泛的参考数据集，我们发现这提高了具有不太灵活的函数形式的快速电位的质量。我们将该技术应用于无序硅，包括模拟玻璃化和多晶晶粒在压力下的形成，系统大小为100万个原子。我们的工作为原子间势模型的ML提供了概念性的见解，并提出了加速凝聚相系统模拟的途径。（c）2022 年作者。除非另有说明，否则所有文章内容均根据 Creative Commons Attribution （CC BY） 许可协议 （http://creativecommons.org/licenses/by/4.0/） 进行许可
展开▼
