Learning molecular dynamics: predicting the dynamics of glasses by a machine learning simulator-Reference-Cited by-同舟云学术

Learning molecular dynamics: predicting the dynamics of glasses by a machine learning simulator

Published:2023 Issue:9 Volume:10 Page:3416-3428
ISSN:2051-6347
Container-title:Materials Horizons
language:en
Short-container-title:Mater. Horiz.

Author:

Liu Han¹^ORCID,Huang Zijie²,Schoenholz Samuel S.³,Cubuk Ekin D.³,Smedskjaer Morten M.⁴^ORCID,Sun Yizhou²,Wang Wei²,Bauchy Mathieu⁵^ORCID

Affiliation:

1. SOlids inFormaTics AI-Laboratory (SOFT-AI-Lab), College of Polymer Science and Engineering, Sichuan University, Chengdu 610065, China

2. Department of Computer Science, University of California, Los Angeles, California, 90095, USA

3. Brain Team, Google Research, Mountain View, California, 94043, USA

4. Department of Chemistry and Bioscience, Aalborg University, Aalborg 9220, Denmark

5. Physics of AmoRphous and Inorganic Solids Laboratory (PARISlab), Department of Civil and Environmental Engineering, University of California, Los Angeles, California, 90095, USA

Abstract

A graph-based machine learning model is built to predict atom dynamics from their static structure, which, in turn, unveils the predictive power of static structure in dynamical evolution of disordered phases.

Funder

National Science Foundation

Publisher

Royal Society of Chemistry (RSC)

Subject

Electrical and Electronic Engineering,Process Chemistry and Technology,Mechanics of Materials,General Materials Science

Link

http://pubs.rsc.org/en/content/articlepdf/2023/MH/D3MH00028A

Reference68 articles.

1. in Molecular dynamics simulations of disordered materials: from network glasses to phase-change memory allyos , ed. C. Massobrio , Springer , Cham Heidelberg , 2015

2. Structure-property relationships from universal signatures of plasticity in disordered solids

3. Molecular Dynamics, Monte Carlo Simulations, and Langevin Dynamics: A Computational Review

4. Machine-learned potentials for next-generation matter simulations

5. Challenges and opportunities in atomistic simulations of glasses: a review

Cited by 5 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. Advancing programmable metamaterials through machine learning-driven buckling strength optimization;Current Opinion in Solid State and Materials Science;2024-08

2. Weak-formulated physics-informed modeling and optimization for heterogeneous digital materials;PNAS Nexus;2024-04-30

3. De Novo Atomistic Discovery of Disordered Mechanical Metamaterials by Machine Learning;Advanced Science;2024-01-25

4. Leveraging graph neural networks and neural operator techniques for high-fidelity mesh-based physics simulations;APL Machine Learning;2023-11-22

5. Bulk and transparent supramolecular glass from evaporation-induced noncovalent polymerization of nucleosides;Materials Horizons;2023