{"id":574003,"date":"2025-09-10T20:23:43","date_gmt":"2025-09-11T00:23:43","guid":{"rendered":"https:\/\/engineering.jhu.edu\/ece\/?post_type=news&p=574003"},"modified":"2025-09-10T20:23:43","modified_gmt":"2025-09-11T00:23:43","slug":"ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds","status":"publish","type":"news","link":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/","title":{"rendered":"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds"},"content":{"rendered":"
\n

A Johns Hopkins engineer has developed a specialized AI tool that could do for materials scientists what ChatGPT has done for coders and writers. The new system, called ChatGPT Materials Explorer, could speed the discovery of everything from advanced batteries to tougher alloys, according to findings appearing in\u00a0<\/span>Integrating Materials and Manufacturing Innovation<\/em><\/a>.<\/span><\/p>\n<\/div>\n

\n

\u201cChatGPT Materials Explorer is like having a specialized research assistant who is trained specifically to dig through huge databases,\u00a0 predict how a material or materials will behave without physical testing, sort through scientific papers to find studies relevant to your projects, and even analyze work and assist with scientific writing,\u201d said ChatGPT Materials Explorer inventor\u00a0<\/span>Kamal Choudhary<\/a>, a professor of materials science and engineering at the Whiting School of Engineering.\u00a0\u00a0<\/span><\/p>\n<\/div>\n

\n

The tool\u2019s key innovation is its access to real scientific data and physics-based models, enabling it to give accurate answers to questions posed by materials scientists. Its creation was inspired by Choudhary\u2019s experiences with ChatGPT.\u00a0\u00a0<\/span><\/p>\n<\/div>\n

\n

\u201cI work on a lot of superconductors, which are materials that conduct electricity without any resistance,\u201d says Choudhary, who also holds a joint appointment in the Department of Electrical and Computer Engineering. \u201cI would ask Chat GPT, \u2018Can you design a superconductor with a particular composition and show me the crystal structure?\u2019 It gave me a very generic response, which turned out to be the wrong answer.\u201d\u00a0\u00a0\u00a0<\/span><\/p>\n<\/div>\n

\n

What Choudhary was experiencing are called hallucinations\u2014when ChatGPT presents false information as factual: a not uncommon occurrence. Some experts estimate that ChatGPT has a hallucination rate of between 10% and 39%.\u00a0<\/span><\/p>\n<\/div>\n

\n

\u201cHallucinations happen because Chat GPT isn\u2019t trained to understand facts,\u201d says Choudhary. \u201cIf it can\u2019t find the exact answer based on the data it\u2019s pulling from, it will say something that sounds plausible. Data sources like Wikipedia or\u00a0<\/span>The New York Times<\/i>\u00a0don\u2019t often include current facts and research about materials science, and can lead to incorrect answers. CME pulls its information from materials science databases, so its answers can be trusted by materials scientists.\u201d<\/span>\u00a0<\/span><\/p>\n<\/div>\n

\n

Choudhary developed his specialized language model with the ChatGPT builder feature, which enables users to create custom GPTs tailored to their needs. He started by telling the AI broadly what he wanted it to do and setting parameters for its functions. Then he configured it, connecting the AI to the databases and instructing it on what kinds of answers it can give.\u00a0<\/span><\/p>\n<\/div>\n

\n

\u201cThese databases are how Chat GPT gets its information, so plugging in databases that are relevant to the field is crucial to getting the correct output from the chatbot,\u201d says Choudhary. \u201cBefore, I would ask regular ChatGPT for the molecular structure notation of ibuprofen, and it would give an incorrect or generic response. With CME, I\u2019ll get the right answer to this and many other materials science questions.\u201d\u00a0<\/span><\/p>\n<\/div>\n

\n

The databases, including National Institute of Science and Technology-Joint Automated Repository for Various Integrated Simulations (NIST-JARVIS), the National Institutes of Health-Chemistry Agent Connecting Tool Usage to Science (NIH-CACTUS), and Materials Project, consistently update CME with the most recent materials science findings, he says.\u00a0<\/span><\/p>\n<\/div>\n

\n

\u201cMaterials Explorer is correct because these databases are automatically updated with new papers; it runs itself and pulls from the newest journals,\u201d says Choudhary.\u00a0\u00a0<\/span><\/p>\n<\/div>\n

\n

To test its resistance to hallucinations, Choudhary compared CME to ChatGPT 4 and ChemCrow, an AI agent geared to solve chemistry-related tasks. From asking the molecular formula for aspirin to interpreting phase diagrams, CME got all eight answers correct, whereas the other models gave only five accurate responses.\u00a0<\/span><\/p>\n<\/div>\n

\n

Choudhary is now working to develop the platform further by adding advanced materials modeling tools, automated literature reviews, and more. He is\u00a0<\/span>also developing an open-source platform which is available at\u00a0<\/span>AtomGPT.org<\/a>. Contrary to the closed-source model of CME, which doesn\u2019t enable users to edit the code that Choudhary established, Atom GPT allows select users to change the code and improve its ability to answer materials science questions.\u00a0\u00a0\u00a0<\/span><\/p>\n<\/div>\n

\n

\u201cThe ultimate goal is to make Chat GPT Materials Explorer the one-stop research assistant that can help materials scientists with computer simulations, data analysis, and other methods that advance the field,\u201d says Choudhary. \u201cWhat started as a fun project on the weekends has turned into something that could be a useful career resource for materials scientists.\u201d\u00a0<\/span><\/p>\n<\/div>\n","protected":false},"template":"","class_list":["post-574003","news","type-news","status-publish","hentry","news_categories-department-news","news_categories-research"],"acf":[],"yoast_head":"\nAI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds - Department of Electrical and Computer 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\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds - Department of Electrical and Computer Engineering\" \/>\n<meta property=\"og:description\" content=\"A Johns Hopkins engineer has developed a specialized AI tool that could do for materials scientists what ChatGPT has done for coders and writers. The new system, called ChatGPT Materials…\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/\" \/>\n<meta property=\"og:site_name\" content=\"Department of Electrical and Computer Engineering\" \/>\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=\"4 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds - Department of Electrical and Computer 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\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/","og_locale":"en_US","og_type":"article","og_title":"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds - Department of Electrical and Computer Engineering","og_description":"A Johns Hopkins engineer has developed a specialized AI tool that could do for materials scientists what ChatGPT has done for coders and writers. The new system, called ChatGPT Materials…","og_url":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/","og_site_name":"Department of Electrical and Computer Engineering","twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/","url":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/","name":"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds - Department of Electrical and Computer Engineering","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/ece\/#website"},"datePublished":"2025-09-11T00:23:43+00:00","breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/ece\/news\/ai-lab-assistant-gets-a-phd-in-materials-new-tool-predicts-material-properties-in-seconds\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/ece\/"},{"@type":"ListItem","position":2,"name":"News","item":"https:\/\/engineering.jhu.edu\/ece\/news\/"},{"@type":"ListItem","position":3,"name":"AI Lab Assistant Gets a PhD in Materials: New Tool Predicts Material Properties in Seconds"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/ece\/#website","url":"https:\/\/engineering.jhu.edu\/ece\/","name":"Department of Electrical and Computer Engineering","description":"Department of Electrical and Computer Engineering","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/ece\/?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 Electrical and Computer Engineering","distributor_original_site_url":"https:\/\/engineering.jhu.edu\/ece","push-errors":false,"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/ece\/wp-json\/wp\/v2\/news\/574003","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/ece\/wp-json\/wp\/v2\/news"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/ece\/wp-json\/wp\/v2\/types\/news"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/ece\/wp-json\/wp\/v2\/media?parent=574003"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}