[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118790-en":3,"doc-seo-118790-105":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},118790,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Explainable Machine Learning for Hydrogen Diffusion in Metals and Random Binary Alloys","Hydrogen diffusion in metals and alloys is crucial for discovering materials that support fuel-cell performance and energy storage. Analytic models may rely on hand-selected features with clear physical meaning but often fail to provide accurate quantitative activation-energy predictions. Machine learning improves accuracy, yet its decision process is hard to interpret. This work builds an interpretable ML framework using a curated database of physical and chemical properties and fits six models to predict hydrogen diffusion activation energies.","Explainable Machine Learning for Hydrogen Diffusion in Metals and  \nRandom Binary Alloys  \narXiv :2308 .07823v1 [ cond-mat .mtrl-sci ] 15 Aug 2023  \nGrace M. Lu, 1 Matthew Witman,2 Sapan Agarwal,2 Vitalie Stavila,2 and Dallas R. Trinkle 1, ∗  \n1 Department of Materials Science and Engineering,  \nUniversity of Illinois at Urbana-Champaign, Urbana, Illinois 61801, USA  \n2 Sandia National Laboratories, Livermore, California 94551, USA  \n(Dated: August 16, 2023)  \nAbstract  \nHydrogen diffusion in metals and alloys plays an important role in the discovery of new materials for fuel cell and energy storage technology. While analytic models use hand-selected features that have clear physical ties to hydrogen diffusion, they often lack accuracy when making quantitative predictions. Machine learning models are capable of making accurate predictions, but their inner workings are obscured, rendering it unclear which physical features are truly important. To develop interpretable machine learning models to predict the activation energies of hydrogen diffusion in metals and random binary alloys, we create a database for physical and chemical properties of the species and use it to fit six machine learning models. Our models achieve root-mean-squared-errors between 98-119 meV on the testing data and accurately predict that elemental Ru has a large activation energy, while elemental Cr and Fe have small activation energies. By analyzing the feature importances of these fitted models, we identify relevant physical properties for predicting hydrogen diffusivity. While metrics for measuring the individual feature importances for machine learning models exist, correlations between the features lead to disagreement between models and limit the conclusions that can be drawn. Instead grouped feature importances, formed by combining the features via their correlations, agree across the six models and reveal that the two groups containing the packing factor and electronic specific heat are particularly significant for predicting hydrogen diffusion in metals and random binary alloys. This framework allows us to interpret machine learning models and enables rapid screening of new materials with the desired rates of hydrogen diffusion.  \nKeywords: hydrogen diffusion; machine-learning; metals; binary alloys  \nI. INTRODUCTION  \nAt present, there is a critical need for sustainable carbon-free energy storage technologies that can address the intermittent and “non-dispatchable” character of renewable energy resources. Hydrogen-based technologies satisfy such requirements and are attainable solutions with a potential for zero-carbon emissions. Hydrogen has the highest gravimetric energy density (121 MJ kg-1 ) of any fuel, is naturally abundant and can be converted into electrical energy via high-efficiency fuel cells [1] . A major hurdle for the use of hydrogen as a clean and efficient energy carrier is developing ways to store and transport it safely and economically. Hydrogen can be stored in gas  \n∗ [dtrinkle@illinois.edu](dtrinkle@illinois.edu)  \nor liquid form inside of high-pressure cylinders [2], primarily for use as a fuel for vehicles, and new materials for these cylinders require slow diffusion rates of hydrogen to both limit leakage and the effects of hydrogen embrittlement [3] . Currently, these tanks are often made of aluminum and its alloys or steels [2] . Hydrogen can also be chemically stored in metal hydrides in solid form [4, 5], but efficient hydrogen absorption and desorption requires fast hydrogen transport through the bulk metal. Two common options are Mg hydrides [6–9], which have high hydrogen storage capabilities but extremely slow kinetics, and Pd hydrides, which have been highly studied because it absorbs hydrogen at room temperature [10] . For all of these storage/transportation options, a quantitative understanding of the interactions of hydrogen with various containment vessels and storage media is essential in the ongoing efforts","cbCaiqB1HxGmfwqK","https://ap.wps.com/l/cbCaiqB1HxGmfwqK","pdf",810020,1,36,"English","en",105,"# Introduction\n## Energy storage motivation\n## Hydrogen storage and transport requirements\n## Background of hydrogen diffusion in lattices\n## Modeling approaches and the need for interpretable ML","[{\"question\":\"Why is hydrogen diffusion in metals and alloys important?\",\"answer\":\"It directly impacts the development of materials for fuel cells and energy storage, where safe storage and efficient transport of hydrogen are required.\"},{\"question\":\"What limitation do analytic models have in predicting hydrogen diffusion?\",\"answer\":\"They often use hand-selected features tied to physical intuition but lack quantitative accuracy when generating activation-energy predictions.\"},{\"question\":\"How does this work make machine learning models interpretable?\",\"answer\":\"It analyzes feature importances from fitted ML models and further uses grouped feature importances formed via feature correlations to identify key physical property groups for hydrogen diffusion.\"}]","Explainable Machine Learning for Hydrogen Diffusion in Metals and Random Binary Alloys | PDF",1785720275,91,{"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},"explainable-machine-learning-for-hydrogen-diffusion-in-metals-and-random-binary-alloys","",{"@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/explainable-machine-learning-for-hydrogen-diffusion-in-metals-and-random-binary-alloys/118790/",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 hydrogen diffusion in metals and alloys important?","Question",{"text":75,"@type":76},"It directly impacts the development of materials for fuel cells and energy storage, where safe storage and efficient transport of hydrogen are required.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitation do analytic models have in predicting hydrogen diffusion?",{"text":80,"@type":76},"They often use hand-selected features tied to physical intuition but lack quantitative accuracy when generating activation-energy predictions.",{"name":82,"@type":73,"acceptedAnswer":83},"How does this work make machine learning models interpretable?",{"text":84,"@type":76},"It analyzes feature importances from fitted ML models and further uses grouped feature importances formed via feature correlations to identify key physical property groups for hydrogen diffusion.","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"]