arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2203.08458cond-mat.mtrl-sciphysics.comp-ph
收藏

复杂合金原子间相互作用势的简单机械学习

Simple machine-learned interatomic potentials for complex alloys

Jesper Byggmästar, Kai Nordlund, Flyura Djurabekova

摘要:

由于训练数据必须采样巨大的配置空间,为包含许多元素的材料开发数据驱动的机器学习原子间势变得越来越具有挑战性。我们研究了机器学习原子间势的学习率和可达到的精度,用于多元素合金,具有不同的局部原子环境描述符组合。我们发现,对于一个五元素合金系统,使用简单的低维描述符的潜力可以达到meV/原子精度与中等大小的训练数据集,显着优于高维SOAP描述符的数据效率,准确性和速度。特别是,我们开发了一个计算快速的机器学习和制表高斯近似势(tabGAP)的Mo-Nb-Ta-V-W合金的两体,三体和一个新的简单的标量多体密度描述符的基础上嵌入原子方法的组合。

英文摘要:

Developing data-driven machine-learning interatomic potentials for materials containing many elements becomes increasingly challenging due to the vast configuration space that must be sampled by the training data. We study the learning rates and achievable accuracy of machine-learning interatomic potentials for many-element alloys with different combinations of descriptors for the local atomic environments. We show that for a five-element alloy system, potentials using simple low-dimensional descriptors can reach meV/atom-accuracy with modestly sized training datasets, significantly outperforming the high-dimensional SOAP descriptor in data efficiency, accuracy, and speed. In particular, we develop a computationally fast machine-learned and tabulated Gaussian approximation potential (tabGAP) for Mo-Nb-Ta-V-W alloys with a combination of two-body, three-body, and a new simple scalar many-body density descriptor based on the embedded atom method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑