[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125541-en":3,"doc-seo-125541-105":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":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},125541,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Machine-learning approach for discovery of conventional superconductors","Machine-learning methods are explored to accelerate the discovery of conventional, hydride-based superconductors whose critical temperature Tc depends on complex, hidden correlations between composition, pressure, and electron-phonon interactions. The study proposes a strategy to predict superconducting behavior at any pressure from atomic structure by learning two electron-phonon interaction parameters, then computing Tc via post-processing. A curated dataset of 584 structures is used for training, validation, and identification of candidate superconductors including at zero pressure.","arXiv :2211 .03265v1 [ cond-mat .supr-con] 7 Nov 2022  \nMachine-learning approach for discovery of conventional superconductors  \nHuan Tran 1, 􀀃 and Tuoc N. Vu2  \n1 School of Materials Science & Engineering, Georgia Institute of Technology, 771 Ferst Dr. NW, Atlanta, GA 30332, USA  \n2 Institute of Engineering Physics, Hanoi University of Science & Technology, 1 Dai Co Viet Rd. , Hanoi 10000, Vietnam  \nFirst-principles computations are the driving force behind numerous discoveries of hydride-based superconductors, mostly at high pressures, during the last decade. Machine-learning (ML) approaches can further accelerate the future discoveries if their reliability can be improved. The main challenge of current ML approaches, typically aiming at predicting the critical temperature Tc of a solid from its chemical composition and target pressure, is that the correlations to be learned are deeply hidden, indirect, and uncertain. In this work, we showed that predicting superconductivity at any pressure from the atomic structure is sustainable and reliable. For a demonstration, we curateda diverse dataset of 584 atomic structures for which 􀀕 and !log , two parameters of the electronphonon interactions, were computed. We then trained some ML models to predict 􀀕 and !log , from which Tc can be computed in a post-processing manner. The models were validated and used to identify two possible superconductors whose Tc ' 10 􀀀 15K and zero pressure. Going forward, this strategy will be improved to better contribute to the discoveries of new superconductors.  \nI. INTRODUCTION  \nIn the search for high critical temperature (Tc ) superconductors, signi􀀌cant progress has been made during the last decade [1{3] . Among thousands of hydride-based superconducting materials computationally predicted [4{ 12], mostly at very high pressures, e.g. , P & 100 GPa, dozens of them, e.g., H3 S [1], LaH 10 [2], and CSH [3], were synthesized and tested. This active research area is presumably motivated by Ashcroft, who, in 2004, predicted [13] that high-Tc superconductivity may be found in hydrogen dominant metallic alloys, probably at high P. Another driving force is the development of 􀀌rstprinciples computational methods to predict material structures at any P [14{20] and to calculate the electronphonon (EP) interactions [21, 22], the atomic mechanism behind the conventional superconductivity, according to the Bardeen-Cooper-Schrie􀀋er (BCS) theory [23] . While critical debates on some discoveries [24{29] are on-going, it seems that the one-day-realized dream of superconductors at ambient conditions may be possible. Readers are referred to some reviews [5, 6, 8, 30] and a recent roadmap [9] for progresses, challenges, and future pathways of this research area.  \nThe central role of 􀀌rst-principles computations in the recent discoveries of conventional superconductors stems  \n􀀓  \nfrom Eliashberg theory [31{34], of which the spectral function 􀀋2 F (!) characterizing the EP interactions could be evaluated numerically. The 􀀌rst inverse moment 􀀕 and logarithmic moment !log of 􀀋 2 F (!), together with an empirical Coulomb pseudopotential 􀀖 􀀃 , are the inputs  \n􀀓  \nto estimate Tc by either solving the Eliashberg equations [31{34] or using the McMillan formula [35{37] (see Sec. II A for more details) . In a typical work􀀍ow (Fig. 1), a search for stable atomic structures accross multiple related chemical compositions is performed at a given pres-  \n􀀃 [huan.tran@mse.gatech.edu](huan.tran@mse.gatech.edu)  \nsure, usually with 􀀌rst-principles computations. Then,􀀋 2 F (!), 􀀕 , !log , and 􀀌nally Tc are evaluated, identifying candidates with high estimated Tc for possible new superconducting materials. Although structure prediction [14{17] and 􀀋2 F (!) computations [21, 22] are extremely expensive and technically non-trivial, signi􀀌cant research e􀀋orts have been devoted to and shaped by this work􀀍ow. Machine-learning (ML) methods have recently emerged in the discoveries of superc","cbCais9D8I4HJS1t","https://ap.wps.com/l/cbCais9D8I4HJS1t","pdf",871060,1,10,"English","en",105,"# Introduction\n## Eliashberg theory inputs for Tc\n## Existing ML workflows and missing links","[{\"question\":\"What is the main limitation of current machine-learning approaches for superconductors?\",\"answer\":\"They try to predict Tc from chemical composition and pressure, but the underlying correlations are deeply hidden, indirect, and uncertain.\"},{\"question\":\"How does this work change the prediction strategy?\",\"answer\":\"It predicts superconductivity at any pressure from atomic structure by learning electron-phonon interaction parameters, then computing Tc in post-processing.\"},{\"question\":\"What dataset and parameters are used in the study?\",\"answer\":\"A curated dataset of 584 atomic structures is used, with two parameters of electron-phonon interactions computed and then predicted by ML models for subsequent Tc calculation.\"}]","Machine-learning approach for discovery of conventional superconductors | PDF",1785899758,25,{"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},"machine-learning-approach-for-discovery-of-conventional-superconductors","",{"@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/machine-learning-approach-for-discovery-of-conventional-superconductors/125541/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main limitation of current machine-learning approaches for superconductors?","Question",{"text":75,"@type":76},"They try to predict Tc from chemical composition and pressure, but the underlying correlations are deeply hidden, indirect, and uncertain.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does this work change the prediction strategy?",{"text":80,"@type":76},"It predicts superconductivity at any pressure from atomic structure by learning electron-phonon interaction parameters, then computing Tc in post-processing.",{"name":82,"@type":73,"acceptedAnswer":83},"What dataset and parameters are used in the study?",{"text":84,"@type":76},"A curated dataset of 584 atomic structures is used, with two parameters of electron-phonon interactions computed and then predicted by ML models for subsequent Tc calculation.","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},[93,97,101,105,110,115,120,123,128,131,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]