Compressing local atomic neighbourhood descriptors

Author:

Darby James P.ORCID,Kermode James R.ORCID,Csányi Gábor

Abstract

AbstractMany atomic descriptors are currently limited by their unfavourable scaling with the number of chemical elements S e.g. the length of body-ordered descriptors, such as the SOAP power spectrum (3-body) and the (ACE) (multiple body-orders), scales as (NS)ν where ν + 1 is the body-order and N is the number of radial basis functions used in the density expansion. We introduce two distinct approaches which can be used to overcome this scaling for the SOAP power spectrum. Firstly, we show that the power spectrum is amenable to lossless compression with respect to both S and N, so that the descriptor length can be reduced from $${{{\mathcal{O}}}}({N}^{2}{S}^{2})$$ O ( N 2 S 2 ) to $${{{\mathcal{O}}}}\left(NS\right)$$ O N S . Secondly, we introduce a generalised SOAP kernel, where compression is achieved through the use of the total, element agnostic density, in combination with radial projection. The ideas used in the generalised kernel are equally applicably to any other body-ordered descriptors and we demonstrate this for the (ACSF).

Funder

Leverhulme Trust

RCUK | Engineering and Physical Sciences Research Council

European Commission

Publisher

Springer Science and Business Media LLC

Subject

Computer Science Applications,Mechanics of Materials,General Materials Science,Modeling and Simulation

Cited by 28 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Chemical-motif characterization of short-range order with E(3)-equivariant graph neural networks;npj Computational Materials;2024-09-13

2. Proper orthogonal descriptors for multi-element chemical systems;Journal of Computational Physics;2024-08

3. HydraScreen: A Generalizable Structure-Based Deep Learning Approach to Drug Discovery;Journal of Chemical Information and Modeling;2024-07-22

4. High Entropy Alloy Composition Design for Mechanical Properties;High Entropy Alloys - Composition and Microstructure Design [Working Title];2024-07-16

5. Overcoming the Chemical Complexity Bottleneck in on-the-Fly Machine Learned Molecular Dynamics Simulations;Journal of Chemical Theory and Computation;2024-07-08

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3