机器学习原子间势的有效等变模型

IF 9.4 1区 材料科学 Q1 CHEMISTRY, PHYSICAL
Ziduo Yang, Xian Wang, Yifan Li, Qiujie Lv, Calvin Yu-Chian Chen, Lei Shen
{"title":"机器学习原子间势的有效等变模型","authors":"Ziduo Yang, Xian Wang, Yifan Li, Qiujie Lv, Calvin Yu-Chian Chen, Lei Shen","doi":"10.1038/s41524-025-01535-3","DOIUrl":null,"url":null,"abstract":"<p>In modern computational materials, machine learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional molecular dynamics (MD) simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, efficient models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce an efficient equivariant graph neural network (E<sup>2</sup>GNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, E<sup>2</sup>GNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains efficient while ensuring prediction accuracy and robustness through the equivariance. Our results show that E<sup>2</sup>GNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct MD simulations using the E<sup>2</sup>GNN force field across solid, liquid, and gas systems. It is found that E<sup>2</sup>GNN can achieve the accuracy of ab initio MD across all examined systems.</p>","PeriodicalId":19342,"journal":{"name":"npj Computational Materials","volume":"30 1","pages":""},"PeriodicalIF":9.4000,"publicationDate":"2025-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Efficient equivariant model for machine learning interatomic potentials\",\"authors\":\"Ziduo Yang, Xian Wang, Yifan Li, Qiujie Lv, Calvin Yu-Chian Chen, Lei Shen\",\"doi\":\"10.1038/s41524-025-01535-3\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In modern computational materials, machine learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional molecular dynamics (MD) simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, efficient models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce an efficient equivariant graph neural network (E<sup>2</sup>GNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, E<sup>2</sup>GNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains efficient while ensuring prediction accuracy and robustness through the equivariance. Our results show that E<sup>2</sup>GNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct MD simulations using the E<sup>2</sup>GNN force field across solid, liquid, and gas systems. It is found that E<sup>2</sup>GNN can achieve the accuracy of ab initio MD across all examined systems.</p>\",\"PeriodicalId\":19342,\"journal\":{\"name\":\"npj Computational Materials\",\"volume\":\"30 1\",\"pages\":\"\"},\"PeriodicalIF\":9.4000,\"publicationDate\":\"2025-02-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"npj Computational Materials\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1038/s41524-025-01535-3\",\"RegionNum\":1,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"npj Computational Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1038/s41524-025-01535-3","RegionNum":1,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
引用次数: 0

摘要

在现代计算材料中,机器学习已经显示出预测原子间电位的能力,从而支持和加速传统的分子动力学(MD)模拟。然而,现有的模型通常会牺牲准确性或效率。此外,高效的模型对于在更低的计算成本下提供更大规模的模拟系统是非常需要的。在这里,我们介绍了一种有效的等变图神经网络(E2GNN),它可以准确有效地预测分子和晶体的原子间电位和力。E2GNN不依赖于高阶表示,而是采用标量向量对偶表示来编码等变特征。通过学习几何对称信息,我们的模型在保证预测精度和稳健性的同时保持了效率。我们的研究结果表明,E2GNN始终优于代表性基线的预测性能,并在不同的数据集(包括催化剂、分子和有机异构体)上实现了显著的效率。此外,我们在固体、液体和气体系统中使用E2GNN力场进行了MD模拟。研究发现,E2GNN在所有被测系统中都能达到从头算MD的精度。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Efficient equivariant model for machine learning interatomic potentials

Efficient equivariant model for machine learning interatomic potentials

In modern computational materials, machine learning has shown the capability to predict interatomic potentials, thereby supporting and accelerating conventional molecular dynamics (MD) simulations. However, existing models typically sacrifice either accuracy or efficiency. Moreover, efficient models are highly demanded for offering simulating systems on a considerably larger scale at reduced computational costs. Here, we introduce an efficient equivariant graph neural network (E2GNN) that can enable accurate and efficient interatomic potential and force predictions for molecules and crystals. Rather than relying on higher-order representations, E2GNN employs a scalar-vector dual representation to encode equivariant features. By learning geometric symmetry information, our model remains efficient while ensuring prediction accuracy and robustness through the equivariance. Our results show that E2GNN consistently outperforms the prediction performance of the representative baselines and achieves significant efficiency across diverse datasets, which include catalysts, molecules, and organic isomers. Furthermore, we conduct MD simulations using the E2GNN force field across solid, liquid, and gas systems. It is found that E2GNN can achieve the accuracy of ab initio MD across all examined systems.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
npj Computational Materials
npj Computational Materials Mathematics-Modeling and Simulation
CiteScore
15.30
自引率
5.20%
发文量
229
审稿时长
6 weeks
期刊介绍: npj Computational Materials is a high-quality open access journal from Nature Research that publishes research papers applying computational approaches for the design of new materials and enhancing our understanding of existing ones. The journal also welcomes papers on new computational techniques and the refinement of current approaches that support these aims, as well as experimental papers that complement computational findings. Some key features of npj Computational Materials include a 2-year impact factor of 12.241 (2021), article downloads of 1,138,590 (2021), and a fast turnaround time of 11 days from submission to the first editorial decision. The journal is indexed in various databases and services, including Chemical Abstracts Service (ACS), Astrophysics Data System (ADS), Current Contents/Physical, Chemical and Earth Sciences, Journal Citation Reports/Science Edition, SCOPUS, EI Compendex, INSPEC, Google Scholar, SCImago, DOAJ, CNKI, and Science Citation Index Expanded (SCIE), among others.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信