[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124136-en":3,"doc-seo-124136-105":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},124136,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","REMatch plus SOS - Machine-learning-accelerated structure prediction for supported metal nanoclusters","Predicting stable structures of nanoclusters is crucial yet computationally demanding, especially for supported metal nanocluster systems where metal–support interactions can strongly modify low-energy configurations. This study introduces a machine learning methodology to accelerate structural prediction by combining local environment descriptors, dimensionality reduction, kernel-based similarity screening, and outlier detection. Rigorous optimization validates the workflow’s ability to identify low-energy global and local minima while markedly reducing computational cost, enabling robust structural screening.","REMatch plus SOS: Machine-learning-accelerated structure prediction for supported metal nanoclusters  \nYunyu Zhang (􀀂􀀂􀀂) , 1 Keith T. Butler  , 1 Michael D. Higham  , 1, 2 and C. Richard A. Catlow 1, 2, 3  \n1 Kathleen Lonsdale Materials Chemistry, Department of Chemistry, University College London,  \n20 Gordon Street, London WC1H 0AJ, United Kingdom  \n2 Research Complex at Harwell, Rutherford Appleton Laboratory, Harwell Oxford, Didcot, Oxon OX11 0FA, United Kingdom  \n3 Cardiff University, School of Chemistry, Main Building, Park Place, Cardiff CF10 3AT, United Kingdom  (Received 4 October 2024; accepted 28 January 2025; published 3 March 2025)  \nPredicting stable structures of nanoclusters is crucial yet computationally demanding. This study presents a machine learning-based methodology designed to accelerate the prediction of stable structures in nanoclusters. By integrating local environment descriptors, with dimensionality reduction, kernel-based similarity measure, and outlier detection, we efficiently screen and select promising configurations, thus accelerating identification of global and local minimum structures. The approach is validated through rigorous optimization, demonstrating its capability to identify low-energy structures while significantly reducing computational costs. This method offers a robust framework for structural screening.  \nDOI: 10.1103/PhysRevMaterials.9.033801  \nI. INTRODUCTION  \nStructure prediction is critically important in materials science, particularly for supported metal nanocluster systems, which have been identified as promising candidates for materials with tailored properties for applications ranging from catalysis, to electronics, to nanotechnology. Due to their small size and large surface area, isolated metal nanoclusters exhibit chemical and physical properties that differ significantly from those of their corresponding bulk materials [1,2] . Furthermore, in practice, metal nanoclusters are almost invariably prepared as adsorbed clusters on some support material; while the support may be considered merely an inert substrate to prevent sintering or nanocluster agglomeration, and thus preserving the high surface area and low coordination environments of the small nanoclusters, it is well established that strong metal-support interactions can result in synergistic effects at metal-support interfaces, which may enhance or inhibit the properties of the material [3–7] . As such, thereis much interest in accurately predicting the structure of low energy structures for supported metal nanoclusters. However, obtaining structural information for small nanoclusters through experiments is challenging, making computational screening a vital tool for predicting these structures. Accurate predictions of nanocluster structures enable the optimization of material performance, providing crucial insights for the design of materials in applications such as catalysis, electronics, and optics.  \nPublished by the American Physical Society under the terms of the Creative Commons Attribution 4 .0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI.  \nTraditional structure prediction methods, such as Monte Carlo simulations [8–10], random quenching [11–13], simulated annealing [14–17], genetic algorithms [18–20], particleswarm algorithms [21–23], and other methods, have been the cornerstone of global optimization techniques for exploring energy landscapes. These studies have predominantly focused on exploring energy landscapes by applying specific global optimization techniques to particular systems [2,24– 27] . While effective, these methods are often computationally intensive, especially when applied to complex systems with large numbers of atoms. The vast configurational space, even for relatively small nanoclusters (i.e. 2–4 nm in diameter), makes exhaustive searches computationally expensive and time-c","cbCaiiUmTnFNT6bH","https://ap.wps.com/l/cbCaiiUmTnFNT6bH","pdf",1547257,1,15,"English","en",105,"# Introduction\n## Motivation for supported nanocluster structure prediction\n## Limits of traditional global optimization methods\n## Role of machine learning in accelerating prediction","[{\"question\":\"Why is structure prediction difficult for supported metal nanoclusters?\",\"answer\":\"Their small size and large surface area make properties differ from bulk materials, and strong metal–support interactions create complex energy landscapes. Experimental structural determination is also challenging, so computational screening is essential but costly.\"},{\"question\":\"What core elements does the proposed machine learning method use?\",\"answer\":\"It integrates local environment descriptors with dimensionality reduction, a kernel-based similarity measure, and outlier detection to screen and select promising configurations efficiently.\"},{\"question\":\"How is the method validated, and what improvement is achieved?\",\"answer\":\"The approach is validated through rigorous optimization, showing it can identify low-energy structures while significantly reducing computational cost compared with exhaustive search strategies.\"}]","REMatch plus SOS - Machine-learning-accelerated structure prediction for supported metal nanoclusters | PDF",1785820649,38,{"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},"rematch-plus-sos-machine-learning-accelerated-structure-prediction-for-supported-metal-nanoclusters","",{"@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/rematch-plus-sos-machine-learning-accelerated-structure-prediction-for-supported-metal-nanoclusters/124136/",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","2026-08-04",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},"Why is structure prediction difficult for supported metal nanoclusters?","Question",{"text":75,"@type":76},"Their small size and large surface area make properties differ from bulk materials, and strong metal–support interactions create complex energy landscapes. Experimental structural determination is also challenging, so computational screening is essential but costly.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What core elements does the proposed machine learning method use?",{"text":80,"@type":76},"It integrates local environment descriptors with dimensionality reduction, a kernel-based similarity measure, and outlier detection to screen and select promising configurations efficiently.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the method validated, and what improvement is achieved?",{"text":84,"@type":76},"The approach is validated through rigorous optimization, showing it can identify low-energy structures while significantly reducing computational cost compared with exhaustive search strategies.","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"]