[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121385-en":3,"doc-seo-121385-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121385,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles - Transferability towards Bulk","We analyze the effectiveness of machine learning (ML) interatomic potentials for modeling gold (Au) nanoparticles, focusing on how well ML models transfer from training systems to larger, near-bulk configurations. The study determines simulation-time and system-size thresholds required for accurate interatomic potentials. Energies and geometries of large Au nanoclusters are compared using VASP and LAMMPS, and the required number of VASP timesteps is quantified to reproduce structural properties. The minimum training-set atomic size is also identified using the LAMMPS Au147 icosahedral heat as reference. Results indicate that modest adjustments to a potential built for one system can generalize to other systems.","nanomaterials   \nArticle  \nEvaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles—Transferability towards Bulk  \nMarco Fronzi 1,2,􀀃, Roger D. Amos 2,􀀃 and Rika Kobayashi 3  \nCitation: Fronzi, M.; Amos, R.D.; Kobayashi, R. Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles—Transferability towards Bulk. Nanomaterials 2023, 13, 1832. [https://doi.org/10.3390/](https://doi.org/10.3390/)  \nnano13121832  \nAcademic Editors: Thomas Ponsand Ming Dao  \nReceived: 27 April 2023  \nRevised: 22 May 2023  \nAccepted: 6 June 2023  \nPublished: 9 June 2023  \nCopyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 School of Chemical and Biomedical Engineering, University of Melbourne, Parkville, VIC 3010, Australia  \n2 School of Mathematical and Physical Sciences, University of Technology Sydney, Ultimo, NSW 2007, Australia  \n3 Supercomputer Facility, Australian National University, Canberra, ACT 2601, Australia; [rika.kobayashi@anu.edu.au](rika.kobayashi@anu.edu.au)  \n* [Correspondence: marco.fronzi@uts.edu.au](Correspondence: marco.fronzi@uts.edu.au) (M.F.); [roger.amos@uts.edu.au](roger.amos@uts.edu.au) (R.D.A)  \nAbstract: 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 Au 147 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.  \nKeywords: machine learning potentials; gold nanoparticles; molecular dynamics; structures; heat capacities  \n1. Introduction  \nFrom the point of view of chemical applications, it is only relatively recently that interest in gold nanoparticles has grown due to discoveries of their usefulness in several fields, including catalysis and biomedical applications [1–4] . Common methods utilised to investigate the properties of gold nanoparticles include quantum mechanical techniques, which provide high accuracy but are computationally demanding and often unfeasible. Molecular dynamics simulations rely on the quality of the underlying interatomic potentials, functions of the potential energy in terms of the atomic positions, and require costly ab initio calculations to obtain chemical accuracy. Machine Learning Interatomic Potentials (ML-IPs) directly target the potential energy surface through neural networks, thus avoiding costly calculations. In our previous work, we investigated their applicability to the properties of gold nanoparticles [5] .  \nTo benchmark against high-accuracy ab initio calculations, we limited ourselves to the 20-atom gold cluster and have discussed related works therein. However, in gold clusters containing up to 20 atoms, all of the gold atoms are located on the surface of the cluster, and it is only for clusters with more than 30 atoms that interior gold atoms become present. Significant internal structure st","cbCairIdYXmLmNi3","https://ap.wps.com/l/cbCairIdYXmLmNi3","pdf",24398181,1,11,"English","en",105,"# Introduction\n## Background and motivation\n## Benchmarking approach and scalability considerations\n# Methods and models\n## ML interatomic potentials\n## VASP and LAMMPS comparisons\n# Transferability analysis\n## Simulation-time and size thresholds\n## Training-set size requirements\n# Results and implications","[{\"question\":\"What is the main goal of the study on ML interatomic potentials for gold nanoparticles?\",\"answer\":\"The work evaluates how effectively machine learning interatomic potentials model gold nanoparticles and how transferable those models are when moving to larger systems toward bulk.\"},{\"question\":\"How do the authors assess transferability to larger gold clusters?\",\"answer\":\"They compare energies and geometries of large Au nanoclusters using VASP and LAMMPS, and determine simulation-time and size thresholds needed for accurate structural reproduction.\"},{\"question\":\"What determines the minimum training-set size in the paper?\",\"answer\":\"The minimum atomic size is investigated by training ML potentials to replicate structural properties of large Au nanoclusters, using the LAMMPS-specific heat of the Au147 icosahedral as a reference.\"}]","Evaluation of Machine Learning Interatomic Potentials for Gold Nanoparticles - Transferability towards Bulk | PDF",1785735402,28,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"evaluation-of-machine-learning-interatomic-potentials-for-gold-nanoparticles-transferability-towards-bulk","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/evaluation-of-machine-learning-interatomic-potentials-for-gold-nanoparticles-transferability-towards-bulk/121385/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of the study on ML interatomic potentials for gold nanoparticles?","Question",{"text":75,"@type":76},"The work evaluates how effectively machine learning interatomic potentials model gold nanoparticles and how transferable those models are when moving to larger systems toward bulk.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the authors assess transferability to larger gold clusters?",{"text":80,"@type":76},"They compare energies and geometries of large Au nanoclusters using VASP and LAMMPS, and determine simulation-time and size thresholds needed for accurate structural reproduction.",{"name":82,"@type":73,"acceptedAnswer":83},"What determines the minimum training-set size in the paper?",{"text":84,"@type":76},"The minimum atomic size is investigated by training ML potentials to replicate structural properties of large Au nanoclusters, using the LAMMPS-specific heat of the Au147 icosahedral as a reference.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]