arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.02237cond-mat.mtrl-sci
收藏

对称限制的能量景观作为机器学习互原子势的基准

Symmetry-restricted energy landscapes as a benchmark for machine learned interatomic potentials

Linköping University(林雪平大学)

Abhijith S Parackal, Rickard Armiento, Florian Trybel

AI总结:

本文通过分析对称限制的能量景观,评估了机器学习互原子势在重现势能面细节方面的准确性和局限性,为未来模型开发提供基准。

摘要:

机器学习互原子势(MLIPs)正成为分子动力学模拟和大尺度晶体能量研究的常用方法。越来越受欢迎的是通用预训练势,也称为基础模型,基于如MACE、CHGNet、M3GNet、ORB和SevenNet等架构。尽管有许多使用验证误差和材料发现任务来评估这些模型的基准,但它们在重现势能面(PES)详细特征方面的精确度并不完全清楚。我们通过系统地探测这些势的预测能量景观来评估这些势的准确性。通过在固定晶体对称性内沿选定的Wyckoff自由度变化原子位置来构建二维切片的势能面。这种方法使互原子势和DFT计算的表面能够进行直接的视觉比较,揭示出可能的潜在问题,例如来自独特局部环境的来源。我们的分析突出了不同势在捕捉局部极小值、鞍点和整体PES拓扑结构方面的优势和限制,为当前预训练IAPs的物理准确性提供了见解,并为未来模型的发展提供了基准。

英文摘要:

Machine learned interatomic potentials (MLIPs) are becoming a standard method for DFT-level accurate molecular dynamics simulation and large-scale studies of crystal energetics. Increasingly popular are universal pre-trained potentials, also called foundation models, based one, e.g. the MACE, CHGNet, M3GNet, ORB, and SevenNet architectures. While there are many benchmarks of these models using validation errors and materials discovery tasks, their fidelity in reproducing the detailed features of potential energy surfaces (PES) is not understood to the same degree. We evaluate the accuracy of these potentials by systematically probing their predicted energy landscapes. Two-dimensional slices of the potential energy surface are constructed where the atomic positions are varied along selected Wyckoff degrees of freedom within a fixed crystal symmetry. This approach enables a direct, visual comparison of the interatomic potentials and DFT-calculated surfaces which reveals potential artifacts e.g., arising from unique local environments. Our analysis highlights the strengths and limitations of different potentials in capturing local minima, saddle points, and overall PES topology, offering insights into the physical accuracy of current pre-trained IAPs and providing benchmarks for future model development.

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。

↑