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 2404.02849cond-mat.mtrl-scicond-mat.dis-nnphysics.comp-ph
收藏

有序、稀布及无规原子结构的高效结构感知特征化与性能预测

Efficient Structure-Informed Featurization and Property Prediction of Ordered, Dilute, and Random Atomic Structures

Adam M. Krajewski, Jonathan W. Siegel, Zi-Kui Liu

AI总结:

本研究针对材料信息学中原子结构特征化工具存在冗余计算的问题,提出三类效率优化方案,在自研工具pySIPFENN中实现了2-10倍的性能提升,且方案可推广至同类工具。

摘要:

结构感知材料信息学是材料科学中一门快速发展的学科,它依托原子结构或构型的特征化,构建向量、体素、图、小图等多种表征形式,可用于机器学习性能预测、指纹识别以及生成式设计。本工作探讨了当前特征化工具通常存在冗余计算的问题,并提出可通过三方面提升效率:一是利用晶体学(轨道)等价性原理优化有序结构的计算;二是基于表征相关的等价性,优化对称性破缺的稀布、掺杂及缺陷结构的计算;三是探讨并对比了在这类表征下近似处理任意晶格中无规固溶体的多种方法。本工作提及的效率提升方案已在作者团队自2019年开发的pySIPFENN(即基于神经网络的结构感知性能与特征工程Python工具集)中实现,针对典型输入的性能提升可达2至10倍。全文中作者还明确阐述了这些进展如何应用于领域内其他同类工具。

英文摘要:

Structure-informed materials informatics is a rapidly evolving discipline of materials science relying on the featurization of atomic structures or configurations to construct vector, voxel, graph, graphlet, and other representations useful for machine learning prediction of properties, fingerprinting, and generative design. This work discusses how current featurizers typically perform redundant calculations and how their efficiency could be improved by considering (1) fundamentals of crystallographic (orbits) equivalency to optimize ordered cases and (2) representation-dependent equivalency to optimize cases of dilute, doped, and defect structures with broken symmetry. It also discusses and contrasts ways of (3) approximating random solid solutions occupying arbitrary lattices under such representations. Efficiency improvements discussed in this work were implemented within pySIPFENN or python toolset for Structure-Informed Property and Feature Engineering with Neural Networks developed by authors since 2019 and shown to increase performance from 2 to 10 times for typical inputs. Throughout this work, the authors explicitly discuss how these advances can be applied to different kinds of similar tools in the community.

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。

↑