[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124155-en":3,"doc-seo-124155-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},124155,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Evaluation of Machine Learning Interatomic Potentials for the Properties of Gold Nanoparticles","Machine learning interatomic potentials are investigated for gold nanoparticles using the DeePMD package with data generated from ab-initio VASP calculations. Benchmarking is performed on Au20 nanoclusters by comparing the ML potential against ab-initio molecular dynamics simulations, demonstrating comparable accuracy with substantially reduced computational cost. The workflow reproduces structural motifs and heat capacities across multiple isomeric forms, and the study contrasts the approach with related ML-IP work to identify directions for future methodological improvements.","nanomaterials   \nArticle  \nEvaluation of Machine Learning Interatomic Potentials for the Properties of Gold Nanoparticles  \nMarco Fronzi 1, *, Roger D. Amos 1, *, Rika Kobayashi 2, Naoki Matsumura 3, Kenta Watanabe 3 and Rafael K. Morizawa 3  \nCitation: Fronzi, M.; Amos, R.D.; Kobayashi, R.; Matsumura, N.;  \nWatanabe, K.; Morizawa, R.K. Evaluation of Machine Learning Interatomic Potentials for the Properties of Gold Nanoparticles. Nanomaterials 2022, 12, 3891. [https://](https://)[ ](https://)[doi.org/10.3390/nano12213891](doi.org/10.3390/nano12213891)  \nAcademic Editor: Paolo M. Scrimin  \nReceived: 8 October 2022  \nAccepted: 26 October 2022  \nPublished: 3 November 2022  \nPublisher's Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.  \nCopyright: © 2022 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 University of Technology Sydney, Ultimo, NSW 2007, Australia  \n2 Australian National University, Canberra, ACT 2601, Australia  \n3 Fujitsu Limited, Kawasaki 211-8588, Japan  \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 have investigated Machine Learning Interatomic Potentials in application to the properties of gold nanoparticles through the DeePMD package, using data generated with the ab-initio VASP program. Benchmarking was carried out on Au 20 nanoclusters against ab-initio molecular dynamics simulations and show we can achieve similar accuracy with the machine learned potential at far reduced cost using LAMMPS. We have been able to reproduce structures and heat capacities of several isomeric forms. Comparison of our workflow with similar ML-IP studies is discussed and has identified areas for future improvement.  \nKeywords: machine learning potentials; gold clusters; molecular dynamics; structures; heat capacities  \n1. Introduction  \nThere is currently a lot of interest in Machine Learning Interatomic Potentials (ML-IP) as a method showing promise of approaching the high accuracy of ab-initio methods, while remaining closer to the cost of empirical classical approaches [1,2] . Classical molecular dynamics (MD) approaches, even though very fast, are not very accurate, and commonly limited in that the force fields cannot break bonds and thus cannot study reactions. Although some work have been done in order to build potentials that can describe chemical reactions, the results are not yet satisfactory [3,4] . Furthermore, many interesting properties, require very long MD runs—much longer than are currently practical with density functional theory (DFT) methods.  \nML-IP have been in existence for several years [5,6] but have gained increased popularity in recent years from the availability of systematic workflows through the development of various software packages such as DeepMD [7,8], Medea [9] or lammps-polymlp [10] . Recent successes in this direction, include application to problems in phase-change materials for memory devices [11], nanoparticle for catalysts [12], carbon-based electrodes for chemical sensing [13] and electrolyte solutions design [14] . This has inspired us to explore ML-IP methodology, starting with a system we are familiar with, to evaluate the feasibility of tackling larger problems such as reactions on surfaces and catalysis.  \nClose colleagues have been interested in gold nanoparticles for many years. There are a variety of questions regarding their structure and properties. Ford et al. [15] have previously studied small clusters using DFT , and more recently larger clusters have been studied with classical MD methods, see e.g., Ref. [16], a","cbCaikDGaGXYm1jg","https://ap.wps.com/l/cbCaikDGaGXYm1jg","pdf",13182630,1,11,"English","en",105,"# Introduction\n# Method\n## ML-IP approach with DeePMD","[{\"question\":\"What machine learning framework and software are used in this study?\",\"answer\":\"The study uses the DeePMD package, with training data generated via ab-initio VASP calculations and evaluation connected to molecular dynamics workflows including LAMMPS for the ML potential execution.\"},{\"question\":\"How is the ML interatomic potential validated?\",\"answer\":\"Validation uses benchmarking on Au20 nanoclusters by directly comparing ML-potential results to ab-initio molecular dynamics simulations, showing similar accuracy while reducing computational cost.\"},{\"question\":\"Which properties of gold nanoparticles are reproduced?\",\"answer\":\"The approach reproduces both structural configurations and heat capacities for several isomeric forms of the gold nanoclusters.\"}]","Evaluation of Machine Learning Interatomic Potentials for the Properties of Gold Nanoparticles | PDF",1785820780,28,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"evaluation-of-machine-learning-interatomic-potentials-for-the-properties-of-gold-nanoparticles","",{"@graph":36,"@context":86},[37,54,69],{"@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-the-properties-of-gold-nanoparticles/124155/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05","2026-08-04",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What machine learning framework and software are used in this study?","Question",{"text":76,"@type":77},"The study uses the DeePMD package, with training data generated via ab-initio VASP calculations and evaluation connected to molecular dynamics workflows including LAMMPS for the ML potential execution.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the ML interatomic potential validated?",{"text":81,"@type":77},"Validation uses benchmarking on Au20 nanoclusters by directly comparing ML-potential results to ab-initio molecular dynamics simulations, showing similar accuracy while reducing computational cost.",{"name":83,"@type":74,"acceptedAnswer":84},"Which properties of gold nanoparticles are reproduced?",{"text":85,"@type":77},"The approach reproduces both structural configurations and heat capacities for several isomeric forms of the gold nanoclusters.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]