{"id":52564,"date":"2025-11-04T11:16:57","date_gmt":"2025-11-04T16:16:57","guid":{"rendered":"https:\/\/engineering.jhu.edu\/materials\/?post_type=news&p=52564"},"modified":"2025-11-21T09:31:21","modified_gmt":"2025-11-21T14:31:21","slug":"when-computers-get-it-wrong","status":"publish","type":"news","link":"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/","title":{"rendered":"When Computers Get It Wrong"},"content":{"rendered":"

In an article appearing in\u00a0<\/span>Nature\u00a0Reviews Materials<\/span><\/i><\/a>,\u00a0researchers including co-author\u00a0Sreenivas Raguraman, a PhD student in the Johns Hopkins\u00a0<\/span>Department of Materials Science and Engineering<\/span><\/a>,\u00a0underscore\u00a0the importance of\u00a0including\u00a0processing techniques\u00a0when employing AI-based calculations\u00a0for materials discovery.<\/span>\u00a0<\/span><\/p>\n

\u201cAI\u00a0has accelerated how we predict material behavior, but these predictions don\u2019t always match what we observe experimentally,\u201d\u00a0says Raguraman, who collaborated with\u00a0Professor of Materials Science and Engineering\u00a0<\/span>Tim Weihs<\/span><\/a>\u00a0and\u00a0Edward J. Schaefer Professor in Chemical and Biomolecular Engineering\u00a0<\/span>Paulette Clancy<\/span><\/a>\u00a0on\u00a0his review. \u201cHow materials are made\u2014their\u00a0processing\u2014\u00a0ultimately\u00a0determines\u00a0the material\u2019s\u00a0performance.\u00a0When processing is excluded, predictions may not translate to real-world outcomes.\u201d<\/span>\u00a0<\/span><\/p>\n

Raguraman highlights how AI and machine learning methods have drastically increased\u00a0the rate of discovery of new materials, but these efforts rarely consider\u00a0the\u00a0processing techniques\u00a0that\u00a0determine\u00a0the stability of a new material.<\/span>\u00a0<\/span><\/p>\n

\u201cIf we\u00a0don\u2019t\u00a0account for processing conditions, we can have all the right\u00a0parts,\u00a0and the material will still fail in the real world.\u00a0It’s\u00a0like baking a cake\u00a0using\u00a0all the right ingredients and following\u00a0the package instructions\u2014only to put it in the freezer instead of the oven,\u201d\u00a0he says.<\/span>\u00a0<\/span><\/p>\n

Raguraman\u00a0emphasizes\u00a0that\u00a0how materials are made is just as important as what they are made of.\u00a0\u00a0The team\u00a0demonstrates\u00a0this concept through case studies on biodegradable magnesium-based alloys used for orthopedic implants, where identical compositions can behave very differently depending on how they are processed. For example, certain heat treatments and deformation routes dramatically change corrosion resistance and mechanical strength without altering chemistry.\u00a0<\/span>\u00a0<\/span><\/p>\n

\u201cIncluding processing in our AI-driven optimization effort will speed the development and adoption of new materials\u00a0as\u00a0more of the design process,\u00a0both\u00a0chemistry and fabrication, are considered,\u201d says\u00a0Weihs.<\/span>\u00a0<\/span><\/p>\n

The authors justify their use of\u00a0magnesium-based\u00a0alloys because their experiments show it performs well in the body and is scalable for manufacturing.\u00a0\u201cHowever, widely used AI frameworks, such as DeepMind\u2019s\u00a0GNoME, \u00a0focus primarily on predicting crystal stability and composition, not on processing pathways\u2014an essential step in determining whether a material can actually be made,\u201d says Raguraman.<\/span>\u00a0<\/span><\/p>\n

To\u00a0bridge this\u00a0gap, co-authors Paulette Clancy\u00a0and Maitreyee\u00a0Sharma Priyadharshini, a professor at Virginia Tech,\u00a0designed\u00a0their\u00a0own\u00a0physics-based\u00a0AI\u00a0framework,\u00a0called PAL 2.0.\u00a0The\u00a0model\u00a0helps\u00a0identify<\/span>\u00a0an alloy\u2019s\u00a0optimal\u00a0processing conditions\u00a0and<\/span>\u00a0better compositions for\u00a0materials\u00a0discovery.\u00a0The\u00a0Hopkins team applied PAL\u00a02.0 to show how focusing on processing, treated as a design variable, can predict better alloy performance.<\/span>\u00a0<\/span><\/p>\n

The team\u00a0suggests\u00a0two\u00a0improvements\u00a0to AI-driven materials discovery:\u00a0improve the data that\u00a0is used in these machine learning\u00a0techniques and\u00a0focus\u00a0on process-aware\u00a0materials design.<\/span>\u00a0<\/span><\/p>\n

\u201cCurrently, processing methods are poorly documented when we are\u00a0predicting\u00a0alloy properties,\u201d\u00a0says\u00a0Clancy. \u201cScientists should\u00a0share all results\u2014not just the successful ones\u2014and ensure\u00a0they\u2019re\u00a0accurate.\u00a0Including that data can help develop AI models that can evolve to consider processing,\u00a0bridging the gap between discovery and deployment to accurately make predictions about how an alloy will perform in real-world applications.\u201d<\/span>\u00a0<\/span><\/p>\n

Raguraman, Weihs, Priyadharshini, and Clancy\u00a0collaborated\u00a0with Adam\u00a0Griebel, senior\u00a0research\u00a0and development engineer at Fort Wayne Metals,\u00a0on\u00a0this article.\u00a0<\/span>\u00a0<\/span><\/p>\n","protected":false},"template":"","class_list":["post-52564","news","type-news","status-publish","hentry"],"acf":[],"yoast_head":"\nWhen Computers Get It Wrong - 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\/when-computers-get-it-wrong\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"When Computers Get It Wrong - Department of Materials Science & Engineering\" \/>\n<meta property=\"og:description\" content=\"In an article appearing in\u00a0Nature\u00a0Reviews Materials,\u00a0researchers including co-author\u00a0Sreenivas Raguraman, a PhD student in the Johns Hopkins\u00a0Department of Materials Science and Engineering,\u00a0underscore\u00a0the importance of\u00a0including\u00a0processing techniques\u00a0when employing AI-based calculations\u00a0for materials discovery.\u00a0 \u201cAI\u00a0has…\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/\" \/>\n<meta property=\"og:site_name\" content=\"Department of Materials Science & Engineering\" \/>\n<meta property=\"article:modified_time\" content=\"2025-11-21T14:31:21+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":"When Computers Get It Wrong - 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\/when-computers-get-it-wrong\/","og_locale":"en_US","og_type":"article","og_title":"When Computers Get It Wrong - Department of Materials Science & Engineering","og_description":"In an article appearing in\u00a0Nature\u00a0Reviews Materials,\u00a0researchers including co-author\u00a0Sreenivas Raguraman, a PhD student in the Johns Hopkins\u00a0Department of Materials Science and Engineering,\u00a0underscore\u00a0the importance of\u00a0including\u00a0processing techniques\u00a0when employing AI-based calculations\u00a0for materials discovery.\u00a0 \u201cAI\u00a0has…","og_url":"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/","og_site_name":"Department of Materials Science & Engineering","article_modified_time":"2025-11-21T14:31:21+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\/when-computers-get-it-wrong\/","url":"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/","name":"When Computers Get It Wrong - Department of Materials Science & Engineering","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/materials\/#website"},"datePublished":"2025-11-04T16:16:57+00:00","dateModified":"2025-11-21T14:31:21+00:00","breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/materials\/news\/when-computers-get-it-wrong\/#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":"When Computers Get It Wrong"}]},{"@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\/52564","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=52564"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}