Extrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H2

Extrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H2 | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Extrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H 2 Yuan Jing, Chenyang Zhang, Mine Shinya, Xiupeng Zhang, Chenxi He, and 9 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6336733/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Selective catalytic reduction of NO x with hydrogen (H 2 -SCR) in the presence of oxygen is an environmentally friendly and sustainable emission control technology that has attracted considerable attention. However, even the most promising currently available catalysts are not sufficiently active to effectively promote this reaction, particularly at low temperatures (< 150°C). Therefore, there is an urgent need for the development of highly active H 2 -SCR catalysts. Although data-science approaches, including machine learning (ML), have been suggested to accelerate the development of catalysts for such important processes, the discovery of unique catalysts using ML remains limited. This limitation stems from a common criticism of ML, namely, its perceived inability to extrapolate and identify extraordinary materials. Herein, we present an extrapolative ML approach for the development of new multi-elemental H 2 -SCR catalysts. Starting with 45 catalysts as the initial dataset, we employed a closed-loop discovery system that combined ML predictions and experimental validation over 24 iterative cycles. This process enabled the experimental testing of 425 catalysts, and the ultimate identification of several catalysts with superior activity (average N₂ yield, %) over previously reported high-performance catalysts in the temperature range of 50–150°C. The optimal catalyst was found to be Pt(1.3)-Ir(0.2)/Ba(1.5)-Co(1)/H-ZSM-5(11). Notably, Co was absent from the original dataset, and the optimal catalyst composition could not be predicted by human experts. Environmental Chemistry Catalysis Artificial Intelligence and Machine Learning machine learning catalysis informatics selective catalytic reduction of NO with H2 (H2-SCR) Full Text Additional Declarations The authors declare no competing interests. Supplementary Files SIMLH2SCRNatSusfinal.docx Extrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H 2 Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6336733","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":435841259,"identity":"7fa8ab71-224b-4cec-a1bb-804ca01e2628","order_by":0,"name":"Yuan Jing","email":"","orcid":"https://orcid.org/0000-0002-6100-8247","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Jing","suffix":""},{"id":435844775,"identity":"c687121c-acd5-447e-9914-e4e33eca8a88","order_by":1,"name":"Chenyang Zhang","email":"","orcid":"","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Chenyang","middleName":"","lastName":"Zhang","suffix":""},{"id":435844776,"identity":"20849b49-3c42-4be0-858c-9c096394cf53","order_by":2,"name":"Mine Shinya","email":"","orcid":"","institution":"Research Institute for Chemical Process Technology, National Institute of Advanced Industrial Science and Technology (AIST)","correspondingAuthor":false,"prefix":"","firstName":"Mine","middleName":"","lastName":"Shinya","suffix":""},{"id":435844777,"identity":"973bd706-2720-4899-9d16-dff054f6537e","order_by":3,"name":"Xiupeng Zhang","email":"","orcid":"","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Xiupeng","middleName":"","lastName":"Zhang","suffix":""},{"id":435844778,"identity":"6940ae6c-b8e6-4ff8-8ce5-7ed9bf2c8915","order_by":4,"name":"Chenxi He","email":"","orcid":"","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Chenxi","middleName":"","lastName":"He","suffix":""},{"id":435844779,"identity":"a8a38728-ed68-4d2e-b8a9-ded17eee0a6c","order_by":5,"name":"Ningqiang Zhang","email":"","orcid":"","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Ningqiang","middleName":"","lastName":"Zhang","suffix":""},{"id":435844780,"identity":"c92834fe-4f58-4e63-bf3d-d99e1acd30fe","order_by":6,"name":"Xu Guo","email":"","orcid":"","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Guo","suffix":""},{"id":435844781,"identity":"af7d0991-c7c0-405e-b57f-51156c4f226c","order_by":7,"name":"Akihiko Anzai","email":"","orcid":"https://orcid.org/0000-0002-8118-407X","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":false,"prefix":"","firstName":"Akihiko","middleName":"","lastName":"Anzai","suffix":""},{"id":435844782,"identity":"92fa87b8-fc21-460b-b37b-abf8ef4512f0","order_by":8,"name":"Kohei Oka","email":"","orcid":"","institution":"Isuzu Advanced Engineering Center, Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Kohei","middleName":"","lastName":"Oka","suffix":""},{"id":435844783,"identity":"87b9235f-940c-4786-90d5-60a051eb3412","order_by":9,"name":"Ryo Toyoshima","email":"","orcid":"","institution":"Department of Materials Engineering, The University of Tokyo","correspondingAuthor":false,"prefix":"","firstName":"Ryo","middleName":"","lastName":"Toyoshima","suffix":""},{"id":435844784,"identity":"1fbd2641-a51c-4d93-9fdb-ce49f7cd7369","order_by":10,"name":"Hiroshi Kondoh","email":"","orcid":"","institution":"Department of Chemistry, Keio University","correspondingAuthor":false,"prefix":"","firstName":"Hiroshi","middleName":"","lastName":"Kondoh","suffix":""},{"id":435844785,"identity":"21f3afa9-699d-4047-bfa4-098354d1d995","order_by":11,"name":"Ichigaku Takigawa","email":"data:image/png;base64,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","orcid":"","institution":"Center for Innovative Research and Education in Data Science (CIREDS), Institute for Liberal Arts and Scieneces, Kyoto University;Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido University","correspondingAuthor":true,"prefix":"","firstName":"Ichigaku","middleName":"","lastName":"Takigawa","suffix":""},{"id":435844786,"identity":"c3d64a4d-4d1c-40c8-835f-29ffb7ab6871","order_by":12,"name":"Ken-ichi Shimizu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIie3QMUvDQBTA8ReEuhx0vVCMX+GFQKfQz3JHIF0OqbuUTHFr1wP9EIVAcTwNmOXENaMuujikCE4ivUSHFpLSbkXuP92F+/EuB2CzHWEUCChAgH69c5J6ycyX381u4ibmzN6kCdUG2Zk7f7p/KCdTnhX5+4tzFwZYRK8KrkZwctM+ZkAvWC6wx5c69hNHx0PUb2biYwTOrWolHiVoCOHLEgxJ8xBLZkjP3FO239Dr65pQnsnT1R8ZVwp+uskARE2QLyhppgyxFKictJu4siEskFpcSp7Ggas/JorPItL1L/RZB5/ie3o2vy4W1SoN/Vkxzqrqa+T5HS+2HdtYEF/uIbY7pwcTm81m+5+tATR3Z68P1dazAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0003-0501-0294","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":true,"prefix":"","firstName":"Ken-ichi","middleName":"","lastName":"Shimizu","suffix":""},{"id":435844787,"identity":"3da6dd6d-eac7-4877-a0f4-eea01a209fdb","order_by":13,"name":"Takashi Toyao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9UlEQVRIiWNgGAWjYNCCChDBw8DYwMDMwMYA4eAEEKkzIAZJWhjbkLQQBPbsPYYfPs6zk7dn4D34cGabtTwfA/PDDwwyd3DbwnPGWHLmtmTDHga+ZMONbemGbQxsxhIMPM9wa5HIMZDm3XaAsYeBx0zyYdthkCPNgOKH8Wkx/s0754A9TIt9GwP7N0JazKR5Gw4kgrVsbDuc2AZk4Ndy5liZ5Yxjyck9h3mMDWecS09uY+YplkjA4xf29ubNNz7U2Nm2t/cYPuwps7ad396+8cPHHtwhxsDAYQCh4TECYiT2HMCjhf0BNtEf+LSMglEwCkbBCAMAGxFK4WEZCmsAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0002-6062-5622","institution":"Institute for Catalysis, Hokkaido University","correspondingAuthor":true,"prefix":"","firstName":"Takashi","middleName":"","lastName":"Toyao","suffix":""}],"badges":[],"createdAt":"2025-03-30 04:32:47","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6336733/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6336733/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79661811,"identity":"70aaf80b-d1ab-456c-b235-30ca3cba36e5","added_by":"auto","created_at":"2025-04-01 09:47:00","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2455783,"visible":true,"origin":"","legend":"","description":"","filename":"MaintextMLH2SCRNatSusfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6336733/v1_covered_b3272a60-8bd6-491d-af36-b3afb0a5f2ba.pdf"},{"id":79658973,"identity":"5ba23b5a-648c-4147-ac94-7a9c3f3cc63c","added_by":"auto","created_at":"2025-04-01 09:22:57","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":14543494,"visible":true,"origin":"","legend":"\u003cp\u003eExtrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e","description":"","filename":"SIMLH2SCRNatSusfinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-6336733/v1/f21e7b3038c4af4002c6d8d8.docx"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eExtrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H\u003csub\u003e2\u003c/sub\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[{"identity":"2acf5233-2f00-4830-993c-f5321dc67700","identifier":"10.13039/501100001691","name":"Japan Society for the Promotion of Science","awardNumber":"22K14538","order_by":0},{"identity":"167048c8-51b2-4222-b51e-6e51a34a8b3e","identifier":"10.13039/501100001691","name":"Japan Society for the Promotion of Science","awardNumber":"24K17564","order_by":1},{"identity":"d2e96af0-7786-4d6f-92b0-37c65485aff4","identifier":"10.13039/501100002241","name":"Japan Science and Technology Agency","awardNumber":"JPMJCR17J3","order_by":2},{"identity":"df2d0ca6-81b5-4059-81e8-25abd222bbe4","identifier":"10.13039/501100002241","name":"Japan Science and Technology Agency","awardNumber":"JPMJFR211U","order_by":3}],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Hokkaido University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"machine learning, catalysis informatics, selective catalytic reduction of NO with H2 (H2-SCR)","lastPublishedDoi":"10.21203/rs.3.rs-6336733/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6336733/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSelective catalytic reduction of NO\u003csub\u003ex\u003c/sub\u003e with hydrogen (H\u003csub\u003e2\u003c/sub\u003e-SCR) in the presence of oxygen is an environmentally friendly and sustainable emission control technology that has attracted considerable attention. However, even the most promising currently available catalysts are not sufficiently active to effectively promote this reaction, particularly at low temperatures (\u0026lt;\u0026thinsp;150\u0026deg;C). Therefore, there is an urgent need for the development of highly active H\u003csub\u003e2\u003c/sub\u003e-SCR catalysts. Although data-science approaches, including machine learning (ML), have been suggested to accelerate the development of catalysts for such important processes, the discovery of unique catalysts using ML remains limited. This limitation stems from a common criticism of ML, namely, its perceived inability to extrapolate and identify extraordinary materials. Herein, we present an extrapolative ML approach for the development of new multi-elemental H\u003csub\u003e2\u003c/sub\u003e-SCR catalysts. Starting with 45 catalysts as the initial dataset, we employed a closed-loop discovery system that combined ML predictions and experimental validation over 24 iterative cycles. This process enabled the experimental testing of 425 catalysts, and the ultimate identification of several catalysts with superior activity (average N₂ yield, %) over previously reported high-performance catalysts in the temperature range of 50\u0026ndash;150\u0026deg;C. The optimal catalyst was found to be Pt(1.3)-Ir(0.2)/Ba(1.5)-Co(1)/H-ZSM-5(11). Notably, Co was absent from the original dataset, and the optimal catalyst composition could not be predicted by human experts.\u003c/p\u003e","manuscriptTitle":"Extrapolative-machine-learning-guided discovery of multi-elemental heterogeneous catalysts for low-temperature NO reduction by H2","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-01 09:22:52","doi":"10.21203/rs.3.rs-6336733/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e9b41ab7-86c2-4324-8e03-6ec38d70eaf0","owner":[],"postedDate":"April 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46406124,"name":"Environmental Chemistry"},{"id":46406125,"name":"Catalysis"},{"id":46406126,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-04-01T09:22:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-01 09:22:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6336733","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6336733","identity":"rs-6336733","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}