[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121431-en":3,"doc-seo-121431-105":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},121431,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Machine Learning Based Prediction of Proton Conductivity in Metal-Organic Frameworks","Machine learning is applied to estimate proton conductivity in metal-organic frameworks (MOFs), motivated by the limited number of reported conductive MOFs and the incomplete understanding of underlying mechanisms. A proton-conductive MOF database is built and used to train both descriptor-based models and transformer-based transfer learning models. The Freeze transformer transfer learning model achieves a mean absolute error (MAE) of 0.91, enabling predictions within one order of magnitude. Feature importance and principal component analysis support interpretation of key factors, guiding targeted MOF design.","Machine Learning Based Prediction of Proton Conductivity in Metal-Organic Frameworks  \nSeunghee Han1, Byoung Gwan Lee2, Dae Woon Lim2, and Jihan Kim1 *  \n1 Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology, Daejeon 34141, Republic of Korea.  \n2 Department of Chemistry and Medical Chemistry, Yonsei University, Wonju, Gangwondo 26493, Republic of  \nKorea  \n*Corresponding author: [jihankim@kaist.ac.kr](jihankim@kaist.ac.kr)  \nABSTRACT  \nRecently, metal-organic frameworks (MOFs) have demonstrated their potential as solid-state electrolytes in proton exchange membrane fuel cells. However, the number of MOFs reported to exhibit proton conductivity remains limited, and the mechanisms underlying this phenomenon are not fully elucidated, complicating the design of proton-conductive MOFs. In response, we developed a comprehensive database of proton-conductive MOFs and applied machine learning techniques to predict their proton conductivity. Our approach included the construction of both descriptor-based and transformer-based models. Notably, the transformer-based transfer learning (Freeze) model performed the best with a mean absolute error (MAE) of 0.91, suggesting that the proton conductivity of MOFs can be estimated within one order of magnitude using this model. Additionally, we employed feature importance and principal component analysis to explore the factors influencing proton conductivity. The insights gained from our database and machine learning model are expected to facilitate the targeted design of proton-conductive MOFs.  \nINTRODUCTION  \nAs interest in sustainable energy grows, energy storage systems (ESS) such as fuel cells (FC) and batteries are increasingly recognized as promising alternatives to fossil fuels. 1, 2 In particular, proton exchange membrane fuel cells (PEMFC) are noted for their high power density and ease of recharging.3 The most conventional material for membrane in these cells is the Nafion membrane, which, despite its widespread use, suffers from issues such as low thermal stability, high cost, and low ion selectivity.4-6 Metal-organic frameworks (MOFs), crystalline porous solid, are emerging as potential materials for these membranes, due to their designability and functionality.7 Traditionally, MOFs have been utilized in fields such as adsorption8, 9, separation10-12, sensing13, 14, and catalysis15, 16. They exhibit high crystallinity, tunable porosity, and the ability to undergo post-synthetic functionalization, demonstrating their potential as solid-state proton conducting membranes. 17, 18 Indeed, proton-conducting MOFs are currently being studied through numerous experiments, yet only a few such materials have been reported.19 In particular, proton conductivity is influenced by the concentration of mobile protons and mobility by conduction pathway determined by the synergistic effects of various factors such as temperature, humidity, and guest molecules, making it challenging to design a MOF with high proton conductivity.7, 20 Additionally, while computational simulations aid in analyzing the mechanisms of MOF proton conductivity, obtaining accurate proton conductivity measurements through simulation proves to be difficult and time-consuming.21, 22  \nTo address this issue, data-driven research might present a viable solution. Various mining tools and algorithms, including text mining, graph mining, Application Programming Interfaces (APIs), and Generative PreTrained Transformers (GPT), have been developed across various materials science fields to obtain specific information about materials.23-28 Research have been conducted to predict the properties of materials and design materials with specific physical properties by developing machine learning models based on data obtained through these methods. Specifically, Bradford et al. collected data on polymer ionic conductivity from publications to discover solid polymer electrolytes (SPE) with high","cbCaiuiIVkwn5BPK","https://ap.wps.com/l/cbCaiuiIVkwn5BPK","pdf",5089478,1,29,"English","en",105,"# Abstract\n# Introduction\n# Results and Discussions\n## Data Extraction and Curation","[{\"question\":\"Why is predicting proton conductivity in MOFs challenging?\",\"answer\":\"Proton conductivity depends on mobile proton concentration and conduction pathways influenced by synergistic factors such as temperature, humidity, and guest molecules. This makes rational design of high-conductivity MOFs difficult.\"},{\"question\":\"What database and data features are used in the study?\",\"answer\":\"The study constructs a database of 248 MOFs including MOF names, DOIs, proton conductivity values, temperature (T), relative humidity (RH), and guest molecule information.\"},{\"question\":\"Which machine learning approach performs best and what is its accuracy?\",\"answer\":\"The transformer-based transfer learning (Freeze) model performs best with a mean absolute error (MAE) of 0.91, indicating conductivity can be estimated within one order of magnitude.\"}]","Machine Learning Based Prediction of Proton Conductivity in Metal-Organic Frameworks | PDF",1785735635,73,{"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-based-prediction-of-proton-conductivity-in-metal-organic-frameworks","",{"@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-based-prediction-of-proton-conductivity-in-metal-organic-frameworks/121431/",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},"Why is predicting proton conductivity in MOFs challenging?","Question",{"text":75,"@type":76},"Proton conductivity depends on mobile proton concentration and conduction pathways influenced by synergistic factors such as temperature, humidity, and guest molecules. This makes rational design of high-conductivity MOFs difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What database and data features are used in the study?",{"text":80,"@type":76},"The study constructs a database of 248 MOFs including MOF names, DOIs, proton conductivity values, temperature (T), relative humidity (RH), and guest molecule information.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning approach performs best and what is its accuracy?",{"text":84,"@type":76},"The transformer-based transfer learning (Freeze) model performs best with a mean absolute error (MAE) of 0.91, indicating conductivity can be estimated within one order of magnitude.","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"]