{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T23:44:45Z","timestamp":1767829485622,"version":"3.49.0"},"reference-count":51,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"vor","delay-in-days":26,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T00:00:00Z","timestamp":1703635200000},"content-version":"tdm","delay-in-days":26,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Army Research Laboratory","award":["W911NF2120040"],"award-info":[{"award-number":["W911NF2120040"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Materials discovery and design typically proceeds through iterative evaluation (both experimental and computational) to obtain data, generally targeting improvement of one or more properties under one or more constraints (e.g. time or budget). However, there can be great variation in the quality and cost of different data, and when they are mixed together in what we here call multifidelity data, the optimal approaches to their utilization are not established. It is therefore important to develop strategies to acquire and use multifidelity data to realize the most efficient iterative materials exploration. In this work, we assess the impact of using multifidelity data through mock demonstration of designing solar cell materials, using the electronic bandgap as the target property. We propose a new approach of using multifidelity data through leveraging machine learning models of both low- and high-fidelity data, where using predicted low-fidelity data as an input feature in the high-fidelity model can improve the impact of a multifidelity data approach. We show how tradeoffs of low- versus high-fidelity measurement cost and acquisition can impact the materials discovery process. We find that the use of multifidelity data has maximal impact on the materials discovery campaign when approximately five low-fidelity measurements per high-fidelity measurement are performed, and when the cost of low-fidelity measurements is approximately 5% or less than that of high-fidelity measurements. This work provides practical guidance and useful qualitative measures for improving materials discovery campaigns that involve multifidelity data.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad1627","type":"journal-article","created":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T06:15:40Z","timestamp":1703657740000},"page":"045060","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Role of multifidelity data in sequential active learning materials discovery campaigns: case study of electronic bandgap"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2229-6730","authenticated-orcid":true,"given":"Ryan","family":"Jacobs","sequence":"first","affiliation":[]},{"given":"Philip E","family":"Goins","sequence":"additional","affiliation":[]},{"given":"Dane","family":"Morgan","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,12,27]]},"reference":[{"key":"mlstad1627bib1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4945422","article-title":"Perspective: materials informatics across the product lifecycle: selection, manufacturing, and certification","volume":"4","author":"Mulholland","year":"2016","journal-title":"APL Mater."},{"key":"mlstad1627bib2","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41524-019-0173-4","article-title":"New frontiers for the materials genome initiative","volume":"5","author":"de Pablo","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib3","doi-asserted-by":"publisher","DOI":"10.1063\/1.4977487","article-title":"Fulfilling the promise of the materials genome initiative with high-throughput experimental methodologies","volume":"4","author":"Green","year":"2017","journal-title":"Appl. Phys. Rev."},{"key":"mlstad1627bib4","doi-asserted-by":"publisher","DOI":"10.1063\/1.4946894","article-title":"Perspective: materials informatics and big data: realization of the \u201cFourth Paradigm\u201d of science in materials science","volume":"4","author":"Agrawal","year":"2016","journal-title":"APL Mater."},{"key":"mlstad1627bib5","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","author":"Butler","year":"2018","journal-title":"Nature"},{"key":"mlstad1627bib6","doi-asserted-by":"publisher","first-page":"83","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 Comput. Mater."},{"key":"mlstad1627bib7","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1146\/annurev-matsci-070218-010015","article-title":"Opportunities and challenges for machine learning in materials science","volume":"50","author":"Morgan","year":"2020","journal-title":"Annu. Rev. Mater. Res."},{"key":"mlstad1627bib8","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s41524-022-00734-6","article-title":"Recent advances and applications of deep learning methods in materials science","volume":"8","author":"Choudhary","year":"2022","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib9","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1038\/s41578-020-00255-y","article-title":"Emerging materials intelligence ecosystems propelled by machine learning","volume":"6","author":"Batra","year":"2021","journal-title":"Nat. Rev. Mater."},{"key":"mlstad1627bib10","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1038\/s41524-019-0153-8","article-title":"Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design","volume":"5","author":"Lookman","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib11","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-022-00899-0","article-title":"Recommender system for discovery of inorganic compounds","volume":"8","author":"Hayashi","year":"2022","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib12","doi-asserted-by":"publisher","first-page":"821","DOI":"10.1557\/mrc.2019.95","article-title":"Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics","volume":"9","author":"Vasudevan","year":"2019","journal-title":"MRS Commun."},{"key":"mlstad1627bib13","doi-asserted-by":"publisher","first-page":"5966","DOI":"10.1038\/s41467-020-19597-w","article-title":"On-the-fly closed-loop materials discovery via Bayesian active learning","volume":"11","author":"Kusne","year":"2020","journal-title":"Nat. Commun."},{"key":"mlstad1627bib14","doi-asserted-by":"publisher","first-page":"8517","DOI":"10.1039\/d0sc01101k","article-title":"Autonomous intelligent agents for accelerated materials discovery","volume":"11","author":"Montoya","year":"2020","journal-title":"Chem. Sci."},{"key":"mlstad1627bib15","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2023-n4pz9","article-title":"Computer-assisted discovery and rational synthesis of ternary oxides","author":"Montoya","year":"2023"},{"key":"mlstad1627bib16","doi-asserted-by":"publisher","first-page":"5312","DOI":"10.1021\/acs.jcim.1c00637","article-title":"NEXTorch: a design and Bayesian optimization toolkit for chemical sciences and engineering","volume":"61","author":"Wang","year":"2021","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad1627bib17","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1038\/s41597-022-01438-8","article-title":"Novel inorganic crystal structures predicted using autonomous simulation agents","volume":"9","author":"Ye","year":"2022","journal-title":"Sci. Data"},{"key":"mlstad1627bib18","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1039\/d2dd00113f","article-title":"Quantifying the performance of machine learning models in materials discovery","volume":"2","author":"Borg","year":"2023","journal-title":"Digit. Discovery"},{"key":"mlstad1627bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-022-08413-8","article-title":"Agents for sequential learning using multiple\u2014fidelity data","volume":"12","author":"Palizhati","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstad1627bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2023.138221","article-title":"Data driven design of alkali-activated concrete using sequential learning","volume":"418","author":"V\u00f6lker","year":"2023","journal-title":"J. Clean Prod."},{"key":"mlstad1627bib21","article-title":"Serendipity based recommender system for perovskites material discovery: balancing exploration and exploitation across multiple models","author":"Venkateswaran Shekar","year":"2022"},{"key":"mlstad1627bib22","doi-asserted-by":"publisher","DOI":"10.1063\/5.0076636","article-title":"Active meta-learning for predicting and selecting perovskite crystallization experiments","volume":"156","author":"Shekar","year":"2022","journal-title":"J. Chem. Phys."},{"key":"mlstad1627bib23","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1080\/27660400.2022.2123263","article-title":"Efficient autonomous material search method combining ab initio calculations, autoencoder, and multi-objective Bayesian optimization","volume":"2","author":"Iwasaki","year":"2022","journal-title":"Sci. Technol. Adv. Mater."},{"key":"mlstad1627bib24","doi-asserted-by":"publisher","first-page":"5854","DOI":"10.1021\/acs.chemmater.0c01894","article-title":"Active learning accelerated discovery of stable iridium oxide polymorphs for the oxygen evolution reaction","volume":"32","author":"Flores","year":"2020","journal-title":"Chem. Mater."},{"key":"mlstad1627bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/adma.201702884","article-title":"Accelerated discovery of large electrostrains in BaTiO3-based piezoelectrics using active learning","volume":"30","author":"Yuan","year":"2018","journal-title":"Adv. Mater."},{"key":"mlstad1627bib26","doi-asserted-by":"publisher","DOI":"10.1038\/srep19660","article-title":"Adaptive strategies for materials design using uncertainties","volume":"6","author":"Balachandran","year":"2016","journal-title":"Sci. Rep."},{"key":"mlstad1627bib27","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.actamat.2019.03.010","article-title":"Machine learning assisted design of high entropy alloys with desired property","volume":"170","author":"Wen","year":"2019","journal-title":"Acta Mater."},{"key":"mlstad1627bib28","doi-asserted-by":"publisher","DOI":"10.1063\/5.0076324","article-title":"Toward autonomous materials research: recent progress and future challenges","volume":"9","author":"Montoya","year":"2022","journal-title":"Appl. Phys. Rev."},{"key":"mlstad1627bib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.pmatsci.2022.101043","article-title":"Toward autonomous laboratories: convergence of artificial intelligence and experimental automation","volume":"132","author":"Xie","year":"2023","journal-title":"Prog. Mater. Sci."},{"key":"mlstad1627bib30","doi-asserted-by":"publisher","first-page":"2169","DOI":"10.1039\/d1mh00495f","article-title":"Toward autonomous design and synthesis of novel inorganic materials","volume":"8","author":"Szymanski","year":"2021","journal-title":"Mater. Horiz."},{"key":"mlstad1627bib31","doi-asserted-by":"publisher","first-page":"2702","DOI":"10.1016\/j.matt.2021.06.036","article-title":"Autonomous experimentation systems for materials development: a community perspective","volume":"4","author":"Stach","year":"2021","journal-title":"Matter"},{"key":"mlstad1627bib32","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1038\/s41578-018-0005-z","article-title":"Accelerating the discovery of materials for clean energy in the era of smart automation","volume":"3","author":"Tabor","year":"2018","journal-title":"Nat. Rev. Mater."},{"key":"mlstad1627bib33","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1038\/s41563-021-01156-3","article-title":"Flexible automation accelerates materials discovery","volume":"21","author":"MacLeod","year":"2022","journal-title":"Nat. Mater."},{"key":"mlstad1627bib34","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1038\/s44160-022-00231-0","article-title":"The rise of self-driving labs in chemical and materials sciences","volume":"2","author":"Abolhasani","year":"2023","journal-title":"Nat. Synth."},{"key":"mlstad1627bib35","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1038\/s41578-023-00588-4","article-title":"Autonomous experiments using active learning and AI","volume":"8","author":"Ren","year":"2023","journal-title":"Nat. Rev. Mater."},{"key":"mlstad1627bib36","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1038\/s41467-022-28580-6","article-title":"A self-driving laboratory advances the pareto front for material properties","volume":"13","author":"MacLeod","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstad1627bib37","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2023-r7b01","article-title":"Autonomous, multi-property-driven molecular discovery: from predictions to measurements and back","author":"Koscher","year":"2023"},{"key":"mlstad1627bib38","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3390\/nano12010012","article-title":"Data-centric architecture for self-driving laboratories with autonomous discovery of new nanomaterials","volume":"12","author":"Butakova","year":"2022","journal-title":"Nanomaterials"},{"key":"mlstad1627bib39","article-title":"Autonomous decision making for solid-state synthesis of inorganic materials","author":"Szymanski","year":"2023"},{"key":"mlstad1627bib40","article-title":"By how much can closed-loop frameworks accelerate computational materials discovery?","author":"Kavalsky","year":"2022"},{"key":"mlstad1627bib41","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1063\/1.1736034","article-title":"Detailed balance limit of efficiency of p-n junction solar cells","volume":"32","author":"Shockley","year":"1961","journal-title":"J. Appl. Phys."},{"key":"mlstad1627bib42","doi-asserted-by":"publisher","DOI":"10.1063\/5.0066009","article-title":"Graph network based deep learning of bandgaps","volume":"155","author":"Li","year":"2021","journal-title":"J. Chem. Phys."},{"key":"mlstad1627bib43","doi-asserted-by":"publisher","DOI":"10.1063\/1.4812323","article-title":"Commentary: the materials project: a materials genome approach to accelerating materials innovation","volume":"1","author":"Jain","year":"2013","journal-title":"APL Mater."},{"key":"mlstad1627bib44","doi-asserted-by":"publisher","first-page":"1501","DOI":"10.1007\/s11837-013-0755-4","article-title":"Materials design and discovery with high-throughput density functional theory: the open quantum materials database (OQMD)","volume":"65","author":"Saal","year":"2013","journal-title":"JOM"},{"key":"mlstad1627bib45","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1016\/j.commatsci.2012.02.005","article-title":"AFLOW: an automatic framework for high-throughput materials discovery","volume":"58","author":"Curtarolo","year":"2012","journal-title":"Comput. Mater. Sci."},{"key":"mlstad1627bib46","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/s41524-020-00440-1","article-title":"The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design","volume":"6","author":"Choudhary","year":"2020","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib47","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2020.109544","article-title":"The materials simulation toolkit for machine learning (MAST-ML): an automated open source toolkit to accelerate data-driven materials research","volume":"176","author":"Jacobs","year":"2020","journal-title":"Comput. Mater. Sci."},{"key":"mlstad1627bib48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/npjcompumats.2016.28","article-title":"A general-purpose machine learning framework for predicting properties of inorganic materials","volume":"2","author":"Ward","year":"2016","journal-title":"npj Comput. Mater."},{"key":"mlstad1627bib49","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.commatsci.2017.03.052","article-title":"Robust FCC solute diffusion predictions from ab-initio machine learning methods","volume":"134","author":"Wu","year":"2017","journal-title":"Comput. Mater. Sci."},{"key":"mlstad1627bib50","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2019.06.010","article-title":"Error assessment and optimal cross-validation approaches in machine learning applied to impurity diffusion","volume":"169","author":"Lu","year":"2019","journal-title":"Comput. Mater. Sci."},{"key":"mlstad1627bib51","doi-asserted-by":"publisher","DOI":"10.1039\/D3DD00117B","article-title":"Multi-fidelity Bayesian optimization of covalent organic frameworks for xenon\/krypton separations","author":"Gantzler","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1627","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1627\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1627\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1627\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,27]],"date-time":"2023-12-27T06:15:44Z","timestamp":1703657744000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad1627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":51,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,12,27]]},"published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad1627","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,1]]},"assertion":[{"value":"Role of multifidelity data in sequential active learning materials discovery campaigns: case study of electronic bandgap","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-15","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-12-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}