Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations
Summary: Machine learning interatomic potential (MLIP) overcomes the challenges of high computational costs in density-functional theory and the relatively low accuracy in classical large-scale molecular dynamics, facilitating more efficient and precise simulations in materials research and design....
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-05-01
|
Series: | iScience |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004224008952 |
_version_ | 1797202926153760768 |
---|---|
author | Guanjie Wang Changrui Wang Xuanguang Zhang Zefeng Li Jian Zhou Zhimei Sun |
author_facet | Guanjie Wang Changrui Wang Xuanguang Zhang Zefeng Li Jian Zhou Zhimei Sun |
author_sort | Guanjie Wang |
collection | DOAJ |
description | Summary: Machine learning interatomic potential (MLIP) overcomes the challenges of high computational costs in density-functional theory and the relatively low accuracy in classical large-scale molecular dynamics, facilitating more efficient and precise simulations in materials research and design. In this review, the current state of the four essential stages of MLIP is discussed, including data generation methods, material structure descriptors, six unique machine learning algorithms, and available software. Furthermore, the applications of MLIP in various fields are investigated, notably in phase-change memory materials, structure searching, material properties predicting, and the pre-trained universal models. Eventually, the future perspectives, consisting of standard datasets, transferability, generalization, and trade-off between accuracy and complexity in MLIPs, are reported. |
first_indexed | 2024-04-24T08:11:12Z |
format | Article |
id | doaj.art-063d1fda4eb0436aa022e09bae572169 |
institution | Directory Open Access Journal |
issn | 2589-0042 |
language | English |
last_indexed | 2024-04-24T08:11:12Z |
publishDate | 2024-05-01 |
publisher | Elsevier |
record_format | Article |
series | iScience |
spelling | doaj.art-063d1fda4eb0436aa022e09bae5721692024-04-17T04:49:46ZengElsevieriScience2589-00422024-05-01275109673Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulationsGuanjie Wang0Changrui Wang1Xuanguang Zhang2Zefeng Li3Jian Zhou4Zhimei Sun5School of Materials Science and Engineering, Beihang University, Beijing 100191, China; School of Integrated Circuit Science and Engineering, Beihang University, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, Beijing 100191, ChinaSchool of Materials Science and Engineering, Beihang University, Beijing 100191, China; Corresponding authorSummary: Machine learning interatomic potential (MLIP) overcomes the challenges of high computational costs in density-functional theory and the relatively low accuracy in classical large-scale molecular dynamics, facilitating more efficient and precise simulations in materials research and design. In this review, the current state of the four essential stages of MLIP is discussed, including data generation methods, material structure descriptors, six unique machine learning algorithms, and available software. Furthermore, the applications of MLIP in various fields are investigated, notably in phase-change memory materials, structure searching, material properties predicting, and the pre-trained universal models. Eventually, the future perspectives, consisting of standard datasets, transferability, generalization, and trade-off between accuracy and complexity in MLIPs, are reported.http://www.sciencedirect.com/science/article/pii/S2589004224008952ChemistryComputer scienceMaterials sciencePhysics |
spellingShingle | Guanjie Wang Changrui Wang Xuanguang Zhang Zefeng Li Jian Zhou Zhimei Sun Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations iScience Chemistry Computer science Materials science Physics |
title | Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations |
title_full | Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations |
title_fullStr | Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations |
title_full_unstemmed | Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations |
title_short | Machine learning interatomic potential: Bridge the gap between small-scale models and realistic device-scale simulations |
title_sort | machine learning interatomic potential bridge the gap between small scale models and realistic device scale simulations |
topic | Chemistry Computer science Materials science Physics |
url | http://www.sciencedirect.com/science/article/pii/S2589004224008952 |
work_keys_str_mv | AT guanjiewang machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations AT changruiwang machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations AT xuanguangzhang machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations AT zefengli machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations AT jianzhou machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations AT zhimeisun machinelearninginteratomicpotentialbridgethegapbetweensmallscalemodelsandrealisticdevicescalesimulations |