{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T14:41:33Z","timestamp":1777905693879,"version":"3.51.4"},"reference-count":71,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T00:00:00Z","timestamp":1594684800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T00:00:00Z","timestamp":1594684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Research Council","award":["Postdoctoral Research Associateship Program"],"award-info":[{"award-number":["Postdoctoral Research Associateship Program"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2020,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Recently there has been an ever-increasing trend in the use of machine learning (ML) and artificial intelligence (AI) methods by the materials science, condensed matter physics, and chemistry communities. This perspective article identifies key scientific, technical, and social opportunities that the materials community must prioritize to consistently develop and leverage Scientific AI (SciAI) to provide a credible path towards the advancement of current materials-limited technologies. Here we highlight the intersections of these opportunities with a series of proposed paths forward. The opportunities are roughly sorted from scientific\/technical (<jats:italic>e.g.<\/jats:italic> development of robust, physically meaningful multiscale material representations) to social (<jats:italic>e.g.<\/jats:italic> promoting an AI-ready workforce). The proposed paths forward range from developing new infrastructure and capabilities to deploying them in industry and academia. We provide a brief introduction to AI in materials science and engineering, followed by detailed discussions of each of the opportunities and paths forward.<\/jats:p>","DOI":"10.1088\/2632-2153\/ab9a20","type":"journal-article","created":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T22:38:03Z","timestamp":1591396683000},"page":"033001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":67,"title":["Scientific AI in materials science: a path to a sustainable and scalable paradigm"],"prefix":"10.1088","volume":"1","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3459-5888","authenticated-orcid":false,"given":"BL","family":"DeCost","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2937-3188","authenticated-orcid":false,"given":"JR","family":"Hattrick-Simpers","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5929-0354","authenticated-orcid":false,"given":"Z","family":"Trautt","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-2087","authenticated-orcid":false,"given":"AG","family":"Kusne","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9808-4112","authenticated-orcid":false,"given":"E","family":"Campo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7871-3148","authenticated-orcid":false,"given":"ML","family":"Green","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2020,7,14]]},"reference":[{"key":"mlstab9a20bib1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4946894","article-title":"Choudhary A Perspective: Materials informatics and big data: Realization of the \u2018fourth paradigm\u2019 of science in materials science","volume":"4","author":"Agrawal","year":"2016","journal-title":"APL Mater."},{"key":"mlstab9a20bib2","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1146\/annurev-matsci-070214-020844","article-title":"Materials data science: current status and future outlook","volume":"45","author":"Kalidindi","year":"2015","journal-title":"Ann. Rev. Mater. Res."},{"key":"mlstab9a20bib3","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/s40192-018-0117-8","article-title":"Perspectives on the impact of machine learning, deep learning and artificial intelligence on materials, processes and structures engineering","volume":"7","author":"Dimiduk","year":"2018","journal-title":"Integrating Mater. Manufacturing Innovation"},{"key":"mlstab9a20bib4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-019-0221-0","article-title":"Recent advances and applications of machine learning in solid-state materials science","volume":"5","author":"Schmidt","year":"2019","journal-title":"npj Computat. Mater."},{"key":"mlstab9a20bib5","doi-asserted-by":"publisher","first-page":"4954","DOI":"10.1021\/acs.chemmater.0c01907","article-title":"Machine learning for materials scientists: An introductory guide towards best practices","volume":"32","author":"Wang","year":"2020","journal-title":"Chem. Mater."},{"key":"mlstab9a20bib6","volume":"vol 6","author":"Holdren","year":"2014"},{"key":"mlstab9a20bib7","article-title":"Materials acceleration platform: Accelerating advanced energy materials discovery by integrating high-throughput methods and artificial intelligence","volume":"6","author":"Aspuru-Guzik","year":"2018","journal-title":"Mission Innovation: Innovation Challenge"},{"key":"mlstab9a20bib8","article-title":"Workshop on artificial intelligence applied to materials discovery and design","author":"","year":"2017","journal-title":"Technical Report"},{"key":"mlstab9a20bib9","article-title":"Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence","author":"","year":"2019"},{"key":"mlstab9a20bib10","article-title":"Machine learning and data \u2013 where you\u2019d least expect it","author":"Aziza","year":"2018"},{"key":"mlstab9a20bib11","doi-asserted-by":"publisher","DOI":"10.1063\/1.4944627","article-title":"Perspective: Codesign for materials science: An optimal learning approach","volume":"4","author":"Lookman","year":"2016","journal-title":"APL Mater."},{"key":"mlstab9a20bib12","doi-asserted-by":"publisher","first-page":"eaaq1566","DOI":"10.1126\/sciadv.aaq1566","article-title":"Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments","volume":"4","author":"Ren","year":"2018","journal-title":"Sci. Adv."},{"key":"mlstab9a20bib13","article-title":"An introduction to statistical design of experiments in metallurgical research","author":"Hussey","year":"1963"},{"key":"mlstab9a20bib14","doi-asserted-by":"publisher","first-page":"pp 317","DOI":"10.1007\/978-94-009-3457-3_24","article-title":"Anisotropic material identification using measured resonant frequencies of rectangular composite plates","volume":"vol 2","author":"De Wilde","year":"1987","journal-title":"Composite Structures 4: Damage Assessment and Material Evaluation"},{"key":"mlstab9a20bib15","first-page":"64","article-title":"Development of a Bayesian acceptance approach for bituminous pavements","volume":"924","author":"Burati","year":"1983","journal-title":"Transport. Res. Record"},{"key":"mlstab9a20bib16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.2495\/AI940071","article-title":"Prediction of composite laminate residual strength based on a neural network approach","volume":"6","author":"Teti","year":"1994","journal-title":"WIT Trans. on Inform. Commun. Technol."},{"key":"mlstab9a20bib17","doi-asserted-by":"publisher","first-page":"966","DOI":"10.2355\/isijinternational.39.966","article-title":"Neural networks in materials science","volume":"39","author":"Bhadeshia","year":"1999","journal-title":"ISIJ Int."},{"key":"mlstab9a20bib18","doi-asserted-by":"publisher","DOI":"10.1063\/1.2755487","article-title":"Rapid structural mapping of ternary metallic alloy systems using the combinatorial approach and cluster analysis","volume":"78","author":"Long","year":"2007","journal-title":"Rev. Sci. Instrum."},{"key":"mlstab9a20bib19","doi-asserted-by":"publisher","DOI":"10.1063\/1.3216809","article-title":"Rapid identification of structural phases in combinatorial thin-film libraries using x-ray diffraction and non-negative matrix factorization","volume":"80","author":"Long","year":"2009","journal-title":"Rev. Sci. Instrum."},{"key":"mlstab9a20bib20","doi-asserted-by":"publisher","first-page":"6367","DOI":"10.1038\/srep06367","article-title":"On-the-fly machine-learning for high-throughput experiments: search for rare-earth-free permanent magnets","volume":"4","author":"Kusne","year":"2014","journal-title":"Sci. Rep."},{"key":"mlstab9a20bib21","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1021\/acscombsci.6b00153","article-title":"Automated phase mapping with AgileFD and its application to light absorber discovery in the V\u2013Mn\u2013Nb oxide system","volume":"19","author":"Suram","year":"2016","journal-title":"ACS Comb. Sci."},{"key":"mlstab9a20bib22","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/S0169-4332(01)01000-5","article-title":"Combinatorial materials research projects in Japan","volume":"189","author":"Koinuma","year":"2002","journal-title":"Appl. Surf. Sci."},{"key":"mlstab9a20bib23","doi-asserted-by":"publisher","first-page":"0894-LL09-07","DOI":"10.1557\/PROC-0894-LL09-07","article-title":"On-line data management for high-throughput experimentation","volume":"894","author":"Lippmaa","year":"2005","journal-title":"MRS Online Proc. Library Archive"},{"key":"mlstab9a20bib24","article-title":"Trends in materials informatics in research on inorganic materials","author":"Chikyow","year":"2006","journal-title":"Technical Report NISTEP Science Technology Foresight Center"},{"key":"mlstab9a20bib25","doi-asserted-by":"publisher","DOI":"10.1038\/npjcompumats.2016.31","article-title":"Autonomy in materials research: a case study in carbon nanotube growth","volume":"2","author":"Nikolaev","year":"2016","journal-title":"npj Computat. Mater."},{"key":"mlstab9a20bib26","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","article-title":"Inverse molecular design using machine learning: Generative models for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science"},{"key":"mlstab9a20bib27","doi-asserted-by":"publisher","DOI":"10.1088\/2515-7639\/ab0c3d","article-title":"Rocketsled: a software library for optimizing high-throughput computational searches","volume":"2","author":"Dunn","year":"2019","journal-title":"J. Phys. Mater."},{"key":"mlstab9a20bib28","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.2.113803","article-title":"Autonomous efficient experiment design for materials discovery with Bayesian model averaging","volume":"2","author":"Talapatra","year":"2018","journal-title":"Phys. Rev. Mater."},{"key":"mlstab9a20bib29","doi-asserted-by":"publisher","first-page":"eaaz1708","DOI":"10.1126\/sciadv.aaz1708","article-title":"Bayesian experimental autonomous researcher for mechanical design","volume":"6","author":"Gongora","year":"2020","journal-title":"Sci. Adv."},{"key":"mlstab9a20bib30","first-page":"275","article-title":"Bias plus variance decomposition for zero-one loss functions","volume":"96","author":"Kohavi","year":"1996","journal-title":"ICML"},{"key":"mlstab9a20bib31","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.patcog.2018.07.025","article-title":"Symmetry-adapted representation learning","volume":"86","author":"Anselmi","year":"2019","journal-title":"Pattern Recognit."},{"key":"mlstab9a20bib32","doi-asserted-by":"crossref","DOI":"10.1038\/s41586-019-1923-7","article-title":"Improved protein structure prediction using potentials from deep learning","author":"Senior","year":"2020"},{"key":"mlstab9a20bib33","first-page":"6571","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"mlstab9a20bib34","author":"Rackauckas","year":"2020"},{"key":"mlstab9a20bib35","article-title":"Zygote: A differentiable programming system to bridge machine learning and scientific computing","author":"Innes","year":"2019"},{"key":"mlstab9a20bib36","doi-asserted-by":"publisher","first-page":"2339","DOI":"10.1038\/s41467-019-10343-5","article-title":"Physically informed artificial neural networks for atomistic modeling of materials","volume":"10","author":"Pun","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstab9a20bib37","article-title":"Practical optimal experiment design with probabilistic programs","author":"Ouyang","year":"2016"},{"key":"mlstab9a20bib38","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1038\/s41586-019-1540-5","article-title":"Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis","volume":"573","author":"Jia","year":"2019","journal-title":"Nature"},{"key":"mlstab9a20bib39","first-page":"141","article-title":"A Bayesian approach to causal discovery","volume":"19","author":"Heckerman","year":"1999","journal-title":"Computat. Causation Discovery"},{"key":"mlstab9a20bib40","author":"Vajda","year":"1972"},{"key":"mlstab9a20bib41","doi-asserted-by":"publisher","first-page":"e0002","DOI":"10.5041\/RMMJ.10102","article-title":"Quasi-periodic crystals\u2014the long road from discovery to acceptance","volume":"4","author":"Shechtman","year":"2013","journal-title":"Rambam Maimonides Med. J."},{"key":"mlstab9a20bib42","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"Imagenet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"mlstab9a20bib43","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/503463a","article-title":"Sharing data in materials science","volume":"503","author":"Tinkle","year":"2013","journal-title":"Nature"},{"key":"mlstab9a20bib44","author":"Ward","year":"2015"},{"key":"mlstab9a20bib45","doi-asserted-by":"publisher","DOI":"10.1063\/1.4944683","article-title":"Research update: The materials genome initiative: Data sharing and the impact of collaborative ab initio databases","volume":"4","author":"Jain","year":"2016","journal-title":"APL Mater."},{"key":"mlstab9a20bib46","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18","article-title":"The fair guiding principles for scientific data management and stewardship","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Scientific Data"},{"key":"mlstab9a20bib47","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1002\/adma.201001763","article-title":"Combinatorial and High-Throughput Screening of Biomaterials","volume":"23","author":"Simon","year":"2011","journal-title":"Adv. Mater."},{"key":"mlstab9a20bib48","doi-asserted-by":"publisher","DOI":"10.1063\/1.4803530","article-title":"Applications of high throughput (combinatorial) methodologies to electronic, magnetic, optical and energy-related materials","volume":"113","author":"Green","year":"2013","journal-title":"J. Appl. Phys."},{"key":"mlstab9a20bib49","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1021\/cr068127f","article-title":"Combinatorial and high-throughput development of sensing materials: the first 10 years","volume":"108","author":"Potyrailo","year":"2008","journal-title":"Chem. Rev."},{"key":"mlstab9a20bib50","doi-asserted-by":"publisher","first-page":"6016","DOI":"10.1002\/anie.200603675","article-title":"Combinatorial and high-throughput materials science","volume":"46","author":"Maier","year":"2007","journal-title":"Angewandte Chemie (Int. Ed. English)"},{"key":"mlstab9a20bib51","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1021\/co200007w","article-title":"Combinatorial and high-throughput screening of materials libraries: review of state of the art","volume":"13","author":"Potyrailo","year":"2011","journal-title":"ACS Combinatorial Sc."},{"key":"mlstab9a20bib52","doi-asserted-by":"publisher","first-page":"1041","DOI":"10.1038\/s41563-019-0402-8","article-title":"Completing the picture through correlative characterization","volume":"1","author":"Burnett","year":"2019","journal-title":"Nat. Mater."},{"key":"mlstab9a20bib53","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"key":"mlstab9a20bib54","article-title":"Program Solicitation NSF 19-526: Materials Innovation Platforms","author":"","year":"2018"},{"key":"mlstab9a20bib55","article-title":"Workshop on advanced energy materials discovery, development, and process design utilizing high-throughput experimental methods, artificial intelligence, autonomous systems, and a collaboratory network","author":"","year":"2018"},{"key":"mlstab9a20bib56","article-title":"20-year community roadmap for artificial intelligence research in the us","author":"Gil","year":"2019"},{"key":"mlstab9a20bib57","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1126\/science.1158722","article-title":"Insights into current limitations of density functional theory","volume":"321","author":"Cohen","year":"2008","journal-title":"Science"},{"key":"mlstab9a20bib58","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/npjcompumats.2015.10","article-title":"The open quantum materials database (OQMD): assessing the accuracy of DFT formation energies","volume":"1","author":"Kirklin","year":"2015","journal-title":"npj Computational Materials"},{"key":"mlstab9a20bib59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.6028\/jres.124.024","article-title":"Improving reproducibility in research: The role of measurement science","volume":"124","author":"Hanisch","year":"2019","journal-title":"J. Res. Natl Inst. Stand. Technol."},{"key":"mlstab9a20bib60","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1038\/d41586-019-02307-y","article-title":"Three pitfalls to avoid in machine learning Nature","volume":"572","author":"Riley","year":"2019"},{"key":"mlstab9a20bib61","article-title":"Quantifying interpretability and trust in machine learning systems","author":"Schmidt","year":"2019"},{"key":"mlstab9a20bib62","article-title":"The promise and peril of human evaluation for model interpretability","author":"Herman","year":"2017"},{"key":"mlstab9a20bib63","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1126\/science.aax0162","article-title":"In defense of the black box","volume":"364","author":"Holm","year":"2019","journal-title":"Science"},{"key":"mlstab9a20bib64","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1038\/nature17439","article-title":"Machine-learning-assisted materials discovery using failed experiments","volume":"533","author":"Raccuglia","year":"2016","journal-title":"Nature"},{"key":"mlstab9a20bib65","author":"","year":"2019"},{"key":"mlstab9a20bib66","author":"Alekseeva","year":"2020"},{"key":"mlstab9a20bib67","author":"Kalidindi","year":"2018"},{"key":"mlstab9a20bib68","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/MCSE.2008.120","article-title":"nanohub. org: Advancing education and research in nanotechnology","volume":"10","author":"Klimeck","year":"2008","journal-title":"Computing Sci. Eng."},{"key":"mlstab9a20bib69","author":"Gastelum","year":"2019"},{"key":"mlstab9a20bib70","author":"Gastelum","year":"2019"},{"key":"mlstab9a20bib71","doi-asserted-by":"publisher","DOI":"10.18434\/T4H01C","article-title":"NIST Special Database 19 - NIST Handprinted Forms and Characters Database","author":"Grother","year":"1995"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T15:38:51Z","timestamp":1645025931000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ab9a20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,14]]},"references-count":71,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2020,7,14]]},"published-print":{"date-parts":[[2020,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ab9a20","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,14]]},"assertion":[{"value":"Scientific AI in materials science: a path to a sustainable and scalable paradigm","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2020 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-03-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-06-05","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-07-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}