{"id":52993,"date":"2025-12-17T14:13:16","date_gmt":"2025-12-17T19:13:16","guid":{"rendered":"https:\/\/engineering.jhu.edu\/materials\/?post_type=news&p=52993"},"modified":"2026-02-06T11:04:50","modified_gmt":"2026-02-06T16:04:50","slug":"the-platinum-problem","status":"publish","type":"news","link":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/","title":{"rendered":"The Platinum Problem"},"content":{"rendered":"

A team of researchers\u00a0in\u00a0the\u00a0<\/span>Department of Materials Science and Engineering<\/span><\/a>\u00a0at Johns Hopkins\u00a0have developed an artificial intelligence framework\u00a0that\u00a0can\u00a0predict the properties for a certain class of alloys called high-entropy alloys (HEAs). Their\u00a0goal is to\u00a0find an alternative to platinum, a\u00a0rare\u00a0element, to accelerate the\u00a0development of hydrogen fuel cells\u00a0for commercial use. Their work is found in\u00a0<\/span>Nano Futures.<\/span><\/i><\/a>\u00a0<\/span><\/p>\n

\u201c<\/span>Hydrogen fuel cells convert hydrogen and oxygen into electricity and water, providing power that is clean and reliable,\u201d<\/span>\u00a0<\/span>says\u00a0project leader\u00a0<\/span>Corey Oses<\/span><\/a>,\u00a0an\u00a0assistant professor\u00a0of materials science and associate\u00a0researcher at the Johns Hopkins<\/span>\u00a0<\/span>Ralph O\u2019Connor Sustainable Energy Institute (ROSEI)<\/span><\/a>.\u00a0\u201cHydrogen power\u00a0is incredibly important at an industrial level, as it can be used\u00a0in long-haul trucking and\u00a0forklifts.\u00a0We want to commercialize hydrogen so regular consumers can use\u00a0it, making\u00a0it the most\u00a0affordable\u00a0choice over\u00a0traditional fuel.\u201d<\/span>\u00a0<\/span><\/p>\n

There\u2019s\u00a0just one problem<\/span>\u2014the conversion from hydrogen to energy\u00a0requires a catalyst\u00a0containing\u00a0platinum<\/span>,\u00a0an expensive,\u00a0rare\u00a0metal.<\/span>\u00a0<\/span><\/p>\n

\u201cWe want to find an alternative to\u00a0platinum,\u00a0so\u00a0it’s\u00a0financially\u00a0feasible\u00a0for consumers to someday make the switch to\u00a0hydrogen power,\u201d says Oses. \u201cHigh-entropy alloys\u00a0are the best option,\u00a0because they are made of many\u00a0components that might be able to mimic or even exceed the emulator,\u00a0out-performing\u00a0a material\u00a0like platinum.\u201d<\/span>\u00a0<\/span><\/p>\n

To find out, they needed to\u00a0discover\u00a0which HEA combinations would\u00a0perform better than platinum.\u00a0The team decided to create an AI framework to predict which combinations would work best as a replacement for platinum.\u00a0<\/span>\u00a0<\/span><\/p>\n

\u201cWe want to quickly screen more compositions and generate rapid predictions,\u00a0so we wondered\u00a0if we could teach an algorithm these\u00a0properties and\u00a0then integrate it into a machine learning\u00a0framework,\u201d says Oses. \u201cAnd the answer is yes, we can.\u201d<\/span>\u00a0<\/span><\/p>\n

Using\u00a0quantum mechanics-based\u00a0calculations\u2014specifically\u00a0<\/span>density functional theory (DFT)\u2014they employed<\/span>\u00a0several methods, called disorder-sensitive descriptors,\u00a0to describe these materials\u00a0computationally\u00a0and then\u00a0fed\u00a0it into the intelligence framework.\u00a0One of these measures, called the disordered enthalpy-entropy descriptor (DEED), is particularly effective at predicting whether\u00a0certain materials can be combined into a stable, complex alloy. They also\u00a0assessed if\u00a0stable\u00a0alloys could\u00a0form\u00a0between\u00a0certain combinations of elements.<\/span>\u00a0<\/span><\/p>\n

\u201cSome of these descriptors are easier to calculate, and some are much more challenging,\u201d says Oses.\u00a0\u201cWe were interested in seeing if the\u00a0easier\u00a0ones, which\u00a0can be calculated\u00a0using a calculator and referencing the periodic table,\u00a0were\u00a0correlated\u00a0with the complex descriptors, which can only be found using DFT. Surprisingly, they are\u00a0loosely related;\u00a0the\u00a0descriptors overlap<\/span>\u00a0and show\u00a0that\u00a0simple descriptors,\u00a0which typically miss detailed electronic\u00a0interactions,\u00a0can\u00a0still\u00a0be useful\u00a0in\u00a0finding\u00a0new materials\u2014even\u00a0if we\u00a0can\u2019t\u00a0directly use them.\u201d<\/span>\u00a0<\/span><\/p>\n

The researchers aim to\u00a0move this\u00a0project\u00a0forward\u00a0by modeling alloys with different structures. \u201cThis work focused on\u00a0a\u00a0crystal structure\u00a0called body-centered cubic,\u00a0which is one of the predominant phases of HEAs,\u201d says Oses.\u00a0\u201cTo get the most\u00a0accurate\u00a0analysis of a potential new material,\u00a0we need to study all the different atomic arrangements a material can have and compare them to one another.\u201d<\/span>\u00a0<\/span><\/p>\n

They also want to make this process\u00a0closed loop,\u00a0so\u00a0the top predictions can be made into<\/span>\u00a0<\/span>experiments that improve the model\u2019s accuracy.\u00a0<\/span>\u00a0<\/span><\/p>\n

\u201cIn the future, we would want to use this technology to see which top predictions meet expectations when they are modeled experimentally and then feed that result back into the model to make predictions that are based on both calculations and experiment,\u201d says Oses. \u201cThis innovation could save us time and money while accelerating the discovery of new materials to take the place of platinum in hydrogen fuel cells.\u201d<\/span>\u00a0<\/span><\/p>\n

Oses collaborated with\u00a0Guangshuai\u00a0Han,\u00a0a postdoctoral fellow\u00a0at\u00a0ROSEI;\u00a0PhD students\u00a0Tianhao Li,\u00a0Xiao Xu,\u00a0\u00a0Jaehyung\u00a0Lee,\u00a0Guotao\u00a0Qiu,\u00a0and\u00a0Sabrina Sequeira;\u00a0and third-year\u00a0Akshaya Ajith, all in the Department of Materials Science and Engineering.<\/span>\u00a0<\/span><\/p>\n","protected":false},"template":"","class_list":["post-52993","news","type-news","status-publish","hentry","news_categories-research"],"acf":[],"yoast_head":"\nThe Platinum Problem - Department of Materials Science & Engineering<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"The Platinum Problem - Department of Materials Science & Engineering\" \/>\n<meta property=\"og:description\" content=\"A team of researchers\u00a0in\u00a0the\u00a0Department of Materials Science and Engineering\u00a0at Johns Hopkins\u00a0have developed an artificial intelligence framework\u00a0that\u00a0can\u00a0predict the properties for a certain class of alloys called high-entropy alloys (HEAs). Their\u00a0goal is…\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/\" \/>\n<meta property=\"og:site_name\" content=\"Department of Materials Science & Engineering\" \/>\n<meta property=\"article:modified_time\" content=\"2026-02-06T16:04:50+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"The Platinum Problem - Department of Materials Science & Engineering","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/","og_locale":"en_US","og_type":"article","og_title":"The Platinum Problem - Department of Materials Science & Engineering","og_description":"A team of researchers\u00a0in\u00a0the\u00a0Department of Materials Science and Engineering\u00a0at Johns Hopkins\u00a0have developed an artificial intelligence framework\u00a0that\u00a0can\u00a0predict the properties for a certain class of alloys called high-entropy alloys (HEAs). Their\u00a0goal is…","og_url":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/","og_site_name":"Department of Materials Science & Engineering","article_modified_time":"2026-02-06T16:04:50+00:00","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/","url":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/","name":"The Platinum Problem - Department of Materials Science & Engineering","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/materials\/#website"},"datePublished":"2025-12-17T19:13:16+00:00","dateModified":"2026-02-06T16:04:50+00:00","breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/materials\/news\/the-platinum-problem\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/materials\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/engineering.jhu.edu\/materials\/news\/"},{"@type":"ListItem","position":3,"name":"The Platinum Problem"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/materials\/#website","url":"https:\/\/engineering.jhu.edu\/materials\/","name":"Department of Materials Science & Engineering","description":"Department of Materials Science & Engineering","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/materials\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"distributor_meta":false,"distributor_terms":false,"distributor_media":false,"distributor_original_site_name":"Department of Materials Science & Engineering","distributor_original_site_url":"https:\/\/engineering.jhu.edu\/materials","push-errors":false,"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/materials\/wp-json\/wp\/v2\/news\/52993","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/materials\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/materials\/wp-json\/wp\/v2\/types\/news"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/materials\/wp-json\/wp\/v2\/media?parent=52993"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}