npj Computational Materials ( IF 9.4 ) Pub Date : 2024-11-17 , DOI: 10.1038/s41524-024-01441-0 Sarath Menon, Yury Lysogorskiy, Alexander L. M. Knoll, Niklas Leimeroth, Marvin Poul, Minaam Qamar, Jan Janssen, Matous Mrovec, Jochen Rohrer, Karsten Albe, Jörg Behler, Ralf Drautz, Jörg Neugebauer
We present a comprehensive and user-friendly framework built upon the pyiron integrated development environment (IDE), enabling researchers to perform the entire Machine Learning Potential (MLP) development cycle consisting of (i) creating systematic DFT databases, (ii) fitting the Density Functional Theory (DFT) data to empirical potentials or MLPs, and (iii) validating the potentials in a largely automatic approach. The power and performance of this framework are demonstrated for three conceptually very different classes of interatomic potentials: an empirical potential (embedded atom method - EAM), neural networks (high-dimensional neural network potentials - HDNNP) and expansions in basis sets (atomic cluster expansion - ACE). As an advanced example for validation and application, we show the computation of a binary composition-temperature phase diagram for Al-Li, a technologically important lightweight alloy system with applications in the aerospace industry.
中文翻译:
使用基于 pyiron 的自动化工作流程,从电子到具有机器学习潜力的相图
我们提出了一个基于 pyiron 集成开发环境 (IDE) 构建的全面且用户友好的框架,使研究人员能够执行整个机器学习潜力 (MLP) 开发周期,包括 (i) 创建系统的 DFT 数据库,(ii) 将密度泛函理论 (DFT) 数据拟合到经验潜力或 MLP,以及 (iii) 以一种很大程度上自动的方法验证潜力。该框架的强大和性能针对三类概念上截然不同的原子间势进行了演示:经验势(嵌入式原子法 - EAM)、神经网络(高维神经网络势 - HDNNP)和基集扩展(原子簇扩展 - ACE)。作为验证和应用的高级示例,我们展示了 Al-Li 的二进制成分-温度相图的计算,Al-Li 是一种技术上重要的轻合金系统,在航空航天工业中得到应用。