arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00957physics.comp-phcond-mat.mtrl-sciphysics.chem-ph
收藏

高保真图深度学习原子间势能的数据高效构建

Data-Efficient Construction of High-Fidelity Graph Deep Learning Interatomic Potentials

Tsz Wai Ko, Shyue Ping Ong

AI总结:

本文提出一种数据高效的多保真度方法构建M3GNet原子间势能,通过将低成本的GGA计算与仅10%的高成本SCAN计算结合训练,在硅和水的案例中达到与8倍SCAN数据训练的单保真度模型相当的精度,从而大幅降低高保真度机器学习势能的开发成本。

摘要:

机器学习势能(MLPs)已成为大规模原子模拟中不可或缺的工具,因为它们能够以极低的计算成本非常准确地重现从头算势能面(PESs)。为了提高计算效率,当今大多数MLP的训练数据是使用相对廉价的密度泛函理论(DFT)方法计算的,例如Perdew-Burke-Ernzerhof(PBE)广义梯度近似(GGA)泛函。元GGA(Meta-GGAs),例如最近开发的强约束且适当赋范(SCAN)泛函,已被证明能够显著改善对多种键合体系中原子相互作用的描述,但其较高的计算成本仍然是其在MLP开发中应用的障碍。在这项工作中,我们提出了一种数据高效的多保真度方法,用于构建Materials 3-body Graph Network(M3GNet)原子间势能,该方法在单一模型中整合了不同层次的理论。以硅和水为例,我们展示了在低保真度GGA计算与10%的高保真度SCAN计算的组合数据集上训练的多保真度M3GNet模型,可以达到与在包含8倍数量SCAN计算的数据集上训练的单保真度M3GNet模型相当的精度。这项工作通过利用现有的低保真度数据集,为以经济高效的方式开发高保真度MLP铺平了道路。

英文摘要:

Machine learning potentials (MLPs) have become an indispensable tool in large-scale atomistic simulations because of their ability to reproduce ab initio potential energy surfaces (PESs) very accurately at a fraction of computational cost. For computational efficiency, the training data for most MLPs today are computed using relatively cheap density functional theory (DFT) methods such as the Perdew-Burke-Ernzerhof (PBE) generalized gradient approximation (GGA) functional. Meta-GGAs such as the recently developed strongly constrained and appropriately normed (SCAN) functional have been shown to yield significantly improved descriptions of atomic interactions for diversely bonded systems, but their higher computational cost remains an impediment to their use in MLP development. In this work, we outline a data-efficient multi-fidelity approach to constructing Materials 3-body Graph Network (M3GNet) interatomic potentials that integrate different levels of theory within a single model. Using silicon and water as examples, we show that a multi-fidelity M3GNet model trained on a combined dataset of low-fidelity GGA calculations with 10% of high-fidelity SCAN calculations can achieve accuracies comparable to a single-fidelity M3GNet model trained on a dataset comprising 8x the number of SCAN calculations. This work paves the way for the development of high-fidelity MLPs in a cost-effective manner by leveraging existing low-fidelity datasets.

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。

↑