[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122820-en":3,"doc-seo-122820-105":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},122820,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Machine Learning Design of Perovskite Catalytic Properties","Discovering new materials that efficiently catalyze oxygen reduction and evolution is essential to scale solid oxide fuel cell and electrolyzer technologies (SOFC/SOEC). The study builds machine learning models to predict key perovskite catalytic properties, including oxygen surface exchange, oxygen diffusivity, and area specific resistance (ASR), using simple elemental features. Results show higher accuracy and dramatically faster predictions than DFT-derived descriptor models, with temperature-dependent ASR, calibrated uncertainty, online accessibility, temporal cross-validation effectiveness, and SHAP-based analysis. Finally, the models screen over 19 million perovskites to identify promising low-cost, stable, high-performance compositions, including mixtures of less-explored elements.","Machine Learning Design of Perovskite Catalytic Properties  \nAuthors: Ryan Jacobs 1,*, Jian Liu2, Harry Abernathy2, Dane Morgan1  \n1 Department of Materials Science and Engineering, University of Wisconsin-Madison, Madison, WI, 53706, USA.  \n2 National Energy Technology Lab, Morgantown, WV, 26505, USA.  \n*Corresponding author e-mail: [rjacobs3@wisc.edu](rjacobs3@wisc.edu)  \nKeywords: oxygen reduction reaction, perovskite, catalysis, machine learning, materials screening  \nAbstract  \nDiscovering new materials that efficiently catalyze the oxygen reduction and evolution reactions is critical for facilitating the widespread adoption of solid oxide fuel cell and electrolyzer (SOFC/SOEC) technologies. Here, we develop machine learning (ML) models to predict perovskite catalytic properties critical for SOFC/SOEC applications, including oxygen surface exchange, oxygen diffusivity, and area specific resistance (ASR) . The models are based on trivial-to-calculate elemental features and are more accurate and dramatically faster than the best models based on ab initio-derived features, potentially eliminating the need for ab initio calculations in descriptor-based screening. Our model of ASR enables temperature-dependent predictions, has well calibrated uncertainty estimates and online accessibility. Use of temporal cross-validation reveals our model to be effective at discovering new promising materials prior to their initial discovery, demonstrating our model can make meaningful predictions. Using the SHapley Additive ExPlanations (SHAP) approach, we provide detailed discussion of different approaches of model featurization for ML property prediction. Finally, we use our model to screen more than 19 million perovskites to develop a list of promising cheap, earth-abundant, stable, and high performing materials, and find some top materials contain mixtures of less-explored elements (e.g., K, Bi, Y, Ni, Cu) worth exploring in more detail.  \nMain  \nA key impediment to more widespread adoption of solid oxide fuel and electrolyzer cell (SOFC/SOEC), including reversible (r-SOFC) and proton ceramic fuel cell (PCFC) 1–12 technologies is the availability of electrode materials which are cheap, stable, and can effectively catalyze the oxygen reduction (ORR, for fuel cells) and evolution (OER, for electrolyzers) reactions at reduced  \noperating temperatures of about 500 °C or even lower.4,5,13 Perovskite oxides are the most popular and well-studied non-precious metal ORR/OER catalysts for current and next generation SOFC/SOEC technologies. Computational discovery of new perovskite electrodes has traditionally centered on the use of first-principles based descriptors of catalytic activity, such as the O p-band center descriptor obtained from density functional theory (DFT) calculations.14 The O p-band center has been successfully used to form correlations with myriad perovskite properties ranging from oxygen surface exchange rates to electronic work function.14–24 However, even the use of descriptors like the O p-band center rely on modestly expensive DFT calculations which places constraints on the speed with which one can propose new materials or understand trends in materials properties, while the use of data-driven machine learning (ML) approaches provides a promising avenue for accelerating both understanding and discovery of new promising materials.  \nThe use of ML approaches in materials science has seen a meteoric rise in recent years.25– 29 However, the prediction of perovskite catalytic properties with ML remains in the nascent stages,30–33 with only a handful of papers using ML to predict properties like ASR and oxygen conductivity.34–37 The O p-band center property correlations mentioned above can be considered a primitive ML model, where the model has a single feature, the O p-band center, and the model type is often a basic univariate linear regressor. It is likely that more sophisticated data-driven techniques can be utilized for und","cbCaikfKDVsWvwVe","https://ap.wps.com/l/cbCaikfKDVsWvwVe","pdf",1345136,1,31,"English","en",105,"# Abstract\n# Motivation and Background\n## Limits of electrode materials and operating temperature\n## Perovskite catalysts and descriptor-based DFT approaches\n# Machine Learning for Catalytic Property Prediction\n## ML growth in materials science\n## Prior ML work on ASR and oxygen conductivity\n# This Work: Data-Centric ML Models\n## Key result 1: property prediction vs O p-band center\n## Key result 2: ASR modeling with featurization and calibration\n## Uncertainty, online access, and temporal validation\n# Explainability and Materials Screening\n## SHAP for featurization discussion\n## Screening of perovskites and candidate selection","[{\"question\":\"What catalytic properties does the machine learning work predict for perovskites?\",\"answer\":\"It predicts oxygen surface exchange, oxygen diffusivity, and area specific resistance (ASR) for perovskite catalytic performance relevant to SOFC/SOEC systems.\"},{\"question\":\"How do the proposed ML models compare with DFT-based descriptor approaches?\",\"answer\":\"The models use trivial-to-calculate elemental features and achieve better accuracy while being dramatically faster than the best DFT descriptor-based models, potentially reducing reliance on ab initio calculations for screening.\"},{\"question\":\"How is the model validated and interpreted to support discovering new materials?\",\"answer\":\"Temporal cross-validation demonstrates the approach can identify promising materials early, and SHAP analysis provides detailed discussion of featurization choices for ML property prediction and model reasoning.\"}]","Machine Learning Design of Perovskite Catalytic Properties | PDF",1785813080,78,{"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},"machine-learning-design-of-perovskite-catalytic-properties","",{"@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/machine-learning-design-of-perovskite-catalytic-properties/122820/",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 catalytic properties does the machine learning work predict for perovskites?","Question",{"text":76,"@type":77},"It predicts oxygen surface exchange, oxygen diffusivity, and area specific resistance (ASR) for perovskite catalytic performance relevant to SOFC/SOEC systems.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How do the proposed ML models compare with DFT-based descriptor approaches?",{"text":81,"@type":77},"The models use trivial-to-calculate elemental features and achieve better accuracy while being dramatically faster than the best DFT descriptor-based models, potentially reducing reliance on ab initio calculations for screening.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the model validated and interpreted to support discovering new materials?",{"text":85,"@type":77},"Temporal cross-validation demonstrates the approach can identify promising materials early, and SHAP analysis provides detailed discussion of featurization choices for ML property prediction and model reasoning.","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"]