[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121148-en":3,"doc-seo-121148-105":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},121148,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Prediction Models for Solid Electrolytes - based on Lattice Dynamics Properties","Machine-learning models are developed to accelerate computational design of advanced solid electrolytes by predicting ionic conductivity beyond static structural descriptors. The study curates dynamic and static feature sets using first-principles phonon calculations, compiling 14 phonon-related descriptors and 16 structural/electronic descriptors. Logistic regression achieves 93% accuracy, while random forest regression reaches 1.179 S/cm RMSE and R2=0.710. Phonon-related features prove essential, and screening 264 Li-containing materials yields 11 promising superionic-conductor candidates.","Machine Learning Prediction Models for Solid Electrolytes based on Lattice Dynamics Properties  \nJiyeon Kim 1,2, Donggeon Lee3,4, Dongwoo Lee5, Xin Li6, Yea-Lee Lee,7 Sooran Kim 1,8*  \n1Department of Physics Education, Kyungpook National University, Daegu 41566, South Korea 2The Center for High Energy Physics, Kyungpook National University, Daegu 41566, South Korea 3Department of Physics, Kyungpook National University, Daegu 41566, South Korea  \n4 SKKU Advanced Institute of Nanotechnology (SAINT) and Department of Nano Engineering, Sungkyunkwan University, Suwon 16419, South Korea  \n5 School of Mechanical Engineering, Sungkyunkwan University, Suwon 16419, South Korea 6John A. Paulson School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA  \n7Chemical Data-Driven Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, South Korea  \n8KNU LAMP Research Center, KNU Institute of Basic Sciences, Kyungpook National University, Daegu, 41566 South Korea  \n*Corresponding authors: [sooran@knu.ac.kr](sooran@knu.ac.kr)  \nABSTRACT  \nRecently, machine-learning approaches have accelerated computational materials design and the search for advanced solid electrolytes. However, the predictors are currently limited to static structural parameters, which may not fully account for the dynamic nature of ionic transport. In this study, we meticulously curated features considering dynamic properties and developed machine-learning models to predict the ionic conductivity of solid electrolytes. We compiled 14 phonon-related descriptors from first-principles phonon calculations along with 16 descriptors related to structure and electronic properties. Our logistic regression classifiers exhibit an accuracy of 93 %, while the random forest regression model yields a root mean square error of 1.179 S/cm and R2 of 0.710. Notably, phonon-related features are essential for estimating the ionic conductivity in both models. Furthermore, we applied our prediction model to screen 264 Licontaining materials and identified 11 promising candidates as potential superionic conductors.  \nTOC GRAPHIC  \nConcomitant to the sharp increase in global demand for electric vehicles, mobile electronics, and large energy storage, lithium-ion batteries (LIBs) have been intensively and extensively studied to improve their performance.1–3 However, organic liquid electrolytes, commonly used in LIBs due to their high ionic mobility, pose potential safety risks.4,5 Thermal instability of LIBsoften arises from the breakage of the separator and electrochemical reactions within the electrolytes.  \nInorganic solid-state electrolytes (SSE) have been investigated to mitigate the safety risks in the past decades.6–11 Compared to liquid electrolytes, SSEs are advantageous in electrochemical and thermal stability, 10 as well as good cycle performance.9,11 It is also possible to operate under high voltage and achieve large energy density by use of the metallic lithium anode and the high voltage cathode.9, 12 Examples include LISICON type (lithium superionic conductor), NASICON type (sodium superionic conductor), garnet, perovskites, and argyrodites materials such as Li 10GeP2 S 12, 13 Li 1.3Al0.3Ti 1.7(PO4)3, 14 Li7La3Zr2O 12, 15 La0.5Li0.5TiO3, 16 and Li6PS5Br.17 However, SSEs exhibit relatively low ionic conductivity compared to organic liquid electrolytes, therefore many studies have searched for SSEs with high ionic conductivity and electrochemical stability.6,18,19  \nPrevious studies have suggested various parameters to control the ionic conductivity of solid electrolytes or superionic conductors. The static structure parameters6 such as bottleneck size,20,21 volume,22,23 and anion sublattice23 have been reported to be related to ionic transport and activation energy. Not only static properties but also dynamic properties have been suggested as important features for ion mobility.6,24–31 For example, low energy optical (LEO)","cbCaidg6yHX9KQFU","https://ap.wps.com/l/cbCaidg6yHX9KQFU","pdf",712474,1,30,"English","en",105,"# Abstract\n## Feature engineering and descriptors\n## Model performance\n## Screening Li-containing materials","[{\"question\":\"Why do static structure features limit current predictors for solid electrolytes?\",\"answer\":\"Static structural parameters cannot fully capture the dynamic nature of ionic transport, motivating the inclusion of lattice dynamics and phonon-related properties.\"},{\"question\":\"What feature sets are used to predict ionic conductivity in this study?\",\"answer\":\"The work compiles 14 phonon-related descriptors from first-principles phonon calculations and 16 descriptors covering structure and electronic properties.\"},{\"question\":\"How accurate are the developed machine-learning models?\",\"answer\":\"Logistic regression classifiers achieve 93% accuracy, while random forest regression yields RMSE of 1.179 S/cm and R2 of 0.710.\"}]","Machine Learning Prediction Models for Solid Electrolytes - based on Lattice Dynamics Properties | PDF",1785734092,76,{"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-prediction-models-for-solid-electrolytes-based-on-lattice-dynamics-properties","",{"@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-prediction-models-for-solid-electrolytes-based-on-lattice-dynamics-properties/121148/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why do static structure features limit current predictors for solid electrolytes?","Question",{"text":75,"@type":76},"Static structural parameters cannot fully capture the dynamic nature of ionic transport, motivating the inclusion of lattice dynamics and phonon-related properties.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What feature sets are used to predict ionic conductivity in this study?",{"text":80,"@type":76},"The work compiles 14 phonon-related descriptors from first-principles phonon calculations and 16 descriptors covering structure and electronic properties.",{"name":82,"@type":73,"acceptedAnswer":83},"How accurate are the developed machine-learning models?",{"text":84,"@type":76},"Logistic regression classifiers achieve 93% accuracy, while random forest regression yields RMSE of 1.179 S/cm and R2 of 0.710.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":21,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]