Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles-Transferability towards Bulk.

Fronzi, M; Amos, RD; Kobayashi, R

Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles-Transferability towards Bulk.

Fronzi, M

Amos, RD Kobayashi, R

Permalink

Publisher:: MDPI
Publication Type:: Journal Article
Citation:: Nanomaterials (Basel), 2023, 13, (12), pp. 1832
Issue Date:: 2023-06-09

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (23.83 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Fronzi, M https://orcid.org/0000-0001-7855-9216
dc.contributor.author	Amos, RD
dc.contributor.author	Kobayashi, R
dc.date.accessioned	2024-03-25T03:22:18Z
dc.date.available	2023-06-06
dc.date.available	2024-03-25T03:22:18Z
dc.date.issued	2023-06-09
dc.identifier.citation	Nanomaterials (Basel), 2023, 13, (12), pp. 1832
dc.identifier.issn	2079-4991
dc.identifier.issn	2079-4991
dc.identifier.uri	http://hdl.handle.net/10453/177079
dc.description.abstract	We analyse the efficacy of machine learning (ML) interatomic potentials (IP) in modelling gold (Au) nanoparticles. We have explored the transferability of these ML models to larger systems and established simulation times and size thresholds necessary for accurate interatomic potentials. To achieve this, we compared the energies and geometries of large Au nanoclusters using VASP and LAMMPS and gained better understanding of the number of VASP simulation timesteps required to generate ML-IPs that can reproduce the structural properties. We also investigated the minimum atomic size of the training set necessary to construct ML-IPs that accurately replicate the structural properties of large Au nanoclusters, using the LAMMPS-specific heat of the Au147 icosahedral as reference. Our findings suggest that minor adjustments to a potential developed for one system can render it suitable for other systems. These results provide further insight into the development of accurate interatomic potentials for modelling Au nanoparticles through machine learning techniques.
dc.format	Electronic
dc.language	eng
dc.publisher	MDPI
dc.relation	http://purl.org/au-research/grants/arc/DP200101217
dc.relation.ispartof	Nanomaterials (Basel)
dc.relation.isbasedon	10.3390/nano13121832
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	0912 Materials Engineering, 1007 Nanotechnology
dc.subject.classification	4016 Materials engineering
dc.subject.classification	4018 Nanotechnology
dc.title	Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles-Transferability towards Bulk.
dc.type	Journal Article
utslib.citation.volume	13
utslib.location.activity	Switzerland
utslib.for	0912 Materials Engineering
utslib.for	1007 Nanotechnology
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Science
pubs.organisational-group	University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	open_access	*
dc.date.updated	2024-03-25T03:22:12Z
pubs.issue	12
pubs.publication-status	Published online
pubs.volume	13
utslib.citation.issue	12

Abstract:

We analyse the efficacy of machine learning (ML) interatomic potentials (IP) in modelling gold (Au) nanoparticles. We have explored the transferability of these ML models to larger systems and established simulation times and size thresholds necessary for accurate interatomic potentials. To achieve this, we compared the energies and geometries of large Au nanoclusters using VASP and LAMMPS and gained better understanding of the number of VASP simulation timesteps required to generate ML-IPs that can reproduce the structural properties. We also investigated the minimum atomic size of the training set necessary to construct ML-IPs that accurately replicate the structural properties of large Au nanoclusters, using the LAMMPS-specific heat of the Au147 icosahedral as reference. Our findings suggest that minor adjustments to a potential developed for one system can render it suitable for other systems. These results provide further insight into the development of accurate interatomic potentials for modelling Au nanoparticles through machine learning techniques.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177079