A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system

Meng, Fan Shun; Shinzato, Shuhei; Zhang, Shihao; Matsubara, Kazuki; Du, Jun Ping; Yu, Peijun; Geng, Wen Tong; Ogata, Shigenobu

doi:https://doi.org/10.1016/j.actamat.2024.120408

A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system

Meng, Fan Shun; Shinzato, Shuhei; Zhang, Shihao et al.

Acta Materialia, 2024, 281, 120408

Number of Access:885（2025-08-14 06:28 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/98584

Link to primary information

File	Format	Terms of use	Size	Views	Date.Available	Description	information
ActaMater_281_120408	pdf	None	8.81 MB	199	2024.12.13

Creative Commons : Attribution

Item Information

Output File Export EndNote Basic Export Mendeley

Title	A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system
Creator	ORCID 0000-0002-2009-1558 0000-0002-2009-1558 researchmap permalink mengfs-ou mengfs-ou CreatorName Meng, Fan Shun
	NRID 1000010853202 1000010853202 researchmap permalink 3201 3201 Scopus Author ID 57188863668 57188863668 CreatorName Shinzato, Shuhei
	CreatorName Zhang, Shihao
	CreatorName Matsubara, Kazuki
	ORCID 0000-0003-4585-1573 0000-0003-4585-1573 CreatorName Du, Jun Ping
	CreatorName Yu, Peijun
	CreatorName Geng, Wen Tong
	NRID 1000020273584 1000020273584 ORCID 0000-0002-9072-4496 0000-0002-9072-4496 researchmap permalink read0185246 read0185246 Scopus Author ID 7201796489 7201796489 CreatorName Ogata, Shigenobu
Subject	Behler–Parrinello neural network potential
	Carbide
	Carbon
	Deep potential
	DFT
	Iron
	Molecular dynamics
Description	Meng F.S., Shinzato S., Zhang S., et al. A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system. Acta Materialia 281, 120408 (2024); https://doi.org/10.1016/j.actamat.2024.120408.
Abstract	Machine learning interatomic potentials (MLIPs) for α-iron and carbon binary system have been constructed aiming for understanding the mechanical behavior of Fe–C steel and carbides. The MLIPs were trained using an extensive reference database produced by spin polarized density functional theory (DFT) calculations. The MLIPs reach the DFT accuracies in many important properties which are frequently engaged in Fe and Fe–C studies, including kinetics and thermodynamics of C in α-Fe with vacancy, grain boundary, and screw dislocation, and basic properties of cementite and cementite–ferrite interfaces. In conjunction with these MLIPs, the impact of C atoms on the mobility of screw dislocation at finite temperature, and the C-decorated core configuration of screw dislocation were investigated, and a uniaxial tensile test on a model with multiple types of defects was conducted.
Publisher	Elsevier B.V.
Source Title	Acta Materialia
Volume (Issue)	281
Page	120408
Date of Issued	2024-12-01
Language	English
Handle URL	https://hdl.handle.net/11094/98584
PISSN	13596454
Relation.isIdenticalTo	DOI (Publisher Version) https://doi.org/10.1016/j.actamat.2024.120408
Access Rights	open access
CopyRight	This article is licensed under a Creative Commons Attribution 4.0 International License.
oaire:version	Version of Record
Category	学術雑誌論文 Journal Article

Resource Type	journal article
Local Type	Journal Article
DCTERMS.bibliographicCitation	Acta Materialia. 2024, 281, p. 120408
DC.title	A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system
DC.creator	Meng, Fan Shun
	Shinzato, Shuhei
	Zhang, Shihao
	Matsubara, Kazuki
	Du, Jun Ping
	Yu, Peijun
	Geng, Wen Tong
	Ogata, Shigenobu
DC.publisher	Elsevier B.V.
DC.language' scheme='DCTERMS.RFC1766	English
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2024-12-01
DC.identifier	https://doi.org/10.1016/j.actamat.2024.120408
DC.subject	Behler–Parrinello neural network potential
	Carbide
	Carbon
	Deep potential
	DFT
	Iron
	Molecular dynamics
DC.description	Meng F.S., Shinzato S., Zhang S., et al. A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system. Acta Materialia 281, 120408 (2024); https://doi.org/10.1016/j.actamat.2024.120408.
DCTERMS.abstract	Machine learning interatomic potentials (MLIPs) for α-iron and carbon binary system have been constructed aiming for understanding the mechanical behavior of Fe–C steel and carbides. The MLIPs were trained using an extensive reference database produced by spin polarized density functional theory (DFT) calculations. The MLIPs reach the DFT accuracies in many important properties which are frequently engaged in Fe and Fe–C studies, including kinetics and thermodynamics of C in α-Fe with vacancy, grain boundary, and screw dislocation, and basic properties of cementite and cementite–ferrite interfaces. In conjunction with these MLIPs, the impact of C atoms on the mobility of screw dislocation at finite temperature, and the C-decorated core configuration of screw dislocation were investigated, and a uniaxial tensile test on a model with multiple types of defects was conducted.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	98584
citation_title	A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system
citation_author	Meng, Fan Shun
	Shinzato, Shuhei
	Zhang, Shihao
	Matsubara, Kazuki
	Du, Jun Ping
	Yu, Peijun
	Geng, Wen Tong
	Ogata, Shigenobu
citation_publisher	Elsevier B.V.
citation_language	English
citation_date	2024-12-01
citation_journal_title	Acta Materialia
citation_volume	281
citation_firstpage	120408
citation_doi	https://doi.org/10.1016/j.actamat.2024.120408
citation_public_url	https://hdl.handle.net/11094/98584

A highly transferable and efficient machine learning interatomic potentials study of α-Fe–C binary system

Link to primary information

Item Information

Show details