[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122404-en":3,"doc-seo-122404-105":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},122404,962075114101,"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 driven search of hydrogen storage materials","Transition to a low-carbon economy requires efficient, sustainable energy-storage solutions, where hydrogen is a promising clean-energy carrier and metal hydrides offer notable hydrogen-storage capacity. This work uses machine learning to predict hydrogen-to-metal (H/M) ratios and solution energies by incorporating thermodynamic parameters and local lattice distortion (LLD) as key features. The best model improves H/M ratios and solution energies across ternary alloys, and Ti-Nb-Mo alloys show composition-dependent effects: Ti, Nb, and V increase capacity while Mo lowers H/M and hydrogen weight percent by 40–50%. Experiments (PCT), DFT, and molecular simulations support the roles of Ti/Nb-promoted diffusion and Mo-mediated hindrance. A Gradient Boosting Regression model identifies LLD as a critical factor, and ML-derived periodic tables support material selection.","Submi&ed to arXiv 03/04/2025 Banerjee et al.  \nMachine learning driven search of hydrogen storage materials  \nT. Banerjee,1,2,+ K. Ji,1,+ W. Xia,1 G. Ouyang,1 T. Del Rose,1 I. Z. Hlova,1 B. Ueland,1 D. D. Johnson,1,3  \nC.-Z. Wang,1 G. Balasubramanian,2 P. Singh1,*  \n1Ames Na(onal Laboratory, US Department of Energy, Iowa State University, Ames, IA 50011, USA  \n2 Department of Mechanical and Industrial Engineering, University of New Haven, West Haven, CT, 06516, USA 3 Department of Materials Science & Engineering, Iowa State University, Ames, IA 50011, USA  \nAbstract  \nThe transiHon to a low-carbon economy demands efficient and sustainable energy-storage soluHons, with hydrogen emerging as a promising clean-energy carrier and with metal hydrides recognized for their hydrogen-storage capacity. Here, we leverage machine learning (ML) to predict hydrogen-tometal (H/M) raHos and soluHon energy by incorporaHng thermodynamic parameters and local laTcedistorHon (LLD) as key features. Our best-performing ML model provides improvements to H/M raHos and soluHon energies over a broad class of ternary alloys (easily extendable to mulH-principal-element alloys), such as Ti-Nb-X (X = Mo, Cr, Hf, Ta, V, Zr) and Co-Ni-X (X = Al, Mg, V) . Ti-Nb-Mo alloys reveal composiHonaleffects in H-storage behavior, in parHcular Ti, Nb, and V enhance H-storage capacity, while Mo reduces H/M and hydrogen weight percent by 40-50% . We a`ributed to slow hydrogen kineHcs in molybdenum rich alloys, which is validated by our pressure-composiHon isotherm (PCT) experiments on pure Ti and Ti5 Mo95 alloys. Density funcHonal theory (DFT) and molecular simulaHons also confirm that Ti and Nb promote H diffusion, whereas Mo hinders it, highlighHng the interplay between electronic structure, laTcedistorHons, and hydrogen uptake. Notably, our Gradient BoosHng Regression model idenHfies LLD as acriHcal factor in H/M predicHons. To aid material selecHon, we present two periodic tables illustraHng elemental effects on (a) H2 wt% and (b) soluHon energy, derived from ML, and provide a reference for idenHfying alloying elements that enhance hydrogen solubility and storage.  \nKeywords: Alloys, ML, DFT, MD, Hydrogen storage, Solu8on energy  \n+ Equal contribuHon  \n* Corresponding author: [psingh84@ameslab.gov/prashant40179@gmail.com](psingh84@ameslab.gov/prashant40179@gmail.com)  \nSubmi&ed to arXiv 03/04/2025 Banerjee et al.  \n1. Introduc0on  \nTransiHoning to a low-carbon economy, hydrogen (H) increasingly garners a`enHon as a key cleanenergy carrier in the shik toward renewable, efficient, and sustainable energy source. It can be produced through electrolysis, using excess electricity from renewable sources and this stored hydrogen can then be uHlized in various ways to generate electricity during periods of high demand or, when renewable generaHon is low, providing a means to balance these intermi`ent energy sources [1–3] . Hydrogen has high energy density by weight making it an a`racHve opHon for storing and transporHng energy efficiently [4] . However, maximizing hydrogen's potenHal as an energy carrier faces conHnued hurdles, especially in storage and transportaHon. Metal hydrides are a`racHve H-storage materials because of their high storage capaciHes and favorable properHes [5,6] .  \nComplex solid-soluHon alloys (CSA) or mulH-principal-element alloys (MPEA) are one such class of materials with vast numbers of unexplored composiHons for adjusHng desired properHes, like H-storage behavior. However, large CSA design space limits efficient exploraHon using Edisonian “trial-and-error”methods in experiments and computaHons [7–12] . ArHficial-intelligence (AI)/ machine-learning (ML) methods, aided by extensive databases of material structures and properHes, has extended design space by enabling robust high-throughput predicHons of material properHes. At the same Hme, it reveals correlaHons and pa`erns between physical factors that convenHonal methods might overlook.  \nAI/ML applicaHons to predic","cbCainPES9GQrrhM","https://ap.wps.com/l/cbCainPES9GQrrhM","pdf",5719395,1,34,"English","en",105,"# Abstract\n# Introduction\n## Motivation for hydrogen as an energy carrier\n## Metal hydrides and complex alloy design challenges\n## AI/ML approaches for predicting hydrogen storage properties","[{\"question\":\"What does the machine learning model predict for hydrogen storage materials?\",\"answer\":\"It predicts hydrogen-to-metal (H/M) ratios and hydrogen solution energy by using thermodynamic parameters and local lattice distortion (LLD) as key features.\"},{\"question\":\"How do Ti, Nb, V, and Mo influence hydrogen-storage behavior in Ti-Nb-X and Ti-Nb-Mo alloys?\",\"answer\":\"Ti, Nb, and V enhance hydrogen-storage capacity, while Mo reduces H/M and hydrogen weight percent by about 40–50%, with effects tied to lattice distortion and hydrogen diffusion behavior.\"},{\"question\":\"What evidence supports the model’s conclusions about Mo slowing hydrogen kinetics?\",\"answer\":\"The study validates the interpretation with pressure-composition isotherm (PCT) experiments on pure Ti and Ti5Mo95 alloys, complemented by DFT and molecular simulations showing Ti/Nb promote H diffusion whereas Mo hinders it.\"}]","Machine learning driven search of hydrogen storage materials | PDF",1785810456,86,{"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-driven-search-of-hydrogen-storage-materials","",{"@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-driven-search-of-hydrogen-storage-materials/122404/",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","2026-08-04",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},"What does the machine learning model predict for hydrogen storage materials?","Question",{"text":75,"@type":76},"It predicts hydrogen-to-metal (H/M) ratios and hydrogen solution energy by using thermodynamic parameters and local lattice distortion (LLD) as key features.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do Ti, Nb, V, and Mo influence hydrogen-storage behavior in Ti-Nb-X and Ti-Nb-Mo alloys?",{"text":80,"@type":76},"Ti, Nb, and V enhance hydrogen-storage capacity, while Mo reduces H/M and hydrogen weight percent by about 40–50%, with effects tied to lattice distortion and hydrogen diffusion behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"What evidence supports the model’s conclusions about Mo slowing hydrogen kinetics?",{"text":84,"@type":76},"The study validates the interpretation with pressure-composition isotherm (PCT) experiments on pure Ti and Ti5Mo95 alloys, complemented by DFT and molecular simulations showing Ti/Nb promote H diffusion whereas Mo hinders it.","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"]