{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T02:23:01Z","timestamp":1790562181729,"version":"4.1.0"},"reference-count":46,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2020,12,29]],"date-time":"2020-12-29T00:00:00Z","timestamp":1609200000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,12,29]],"date-time":"2020-12-29T00:00:00Z","timestamp":1609200000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100006151","name":"Basic Energy Sciences","doi-asserted-by":"crossref","award":["DE-FOA-0001912"],"award-info":[{"award-number":["DE-FOA-0001912"]}],"id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Machine learning surrogate models for quantum mechanical simulations have enabled the field to efficiently and accurately study material and molecular systems. Developed models typically rely on a substantial amount of data to make reliable predictions of the potential energy landscape or careful active learning (AL) and uncertainty estimates. When starting with small datasets, convergence of AL approaches is a major outstanding challenge which has limited most demonstrations to online AL. In this work we demonstrate a \u0394-machine learning (ML) approach that enables stable convergence in offline AL strategies by avoiding unphysical configurations with initial datasets as little as a single data point. We demonstrate our framework\u2019s capabilities on a structural relaxation, transition state calculation, and molecular dynamics simulation, with the number of first principle calculations being cut down anywhere from 70%\u201390%. The approach is incorporated and developed alongside AMP<jats:italic>torch<\/jats:italic>, an open-source ML potential package, along with interactive Google Colab notebook examples.<\/jats:p>","DOI":"10.1088\/2632-2153\/abcc44","type":"journal-article","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T06:31:44Z","timestamp":1605853904000},"page":"025007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Enabling robust offline active learning for machine learning potentials using simple physics-based priors"],"prefix":"10.1088","volume":"2","author":[{"given":"Muhammed","family":"Shuaibi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saurabh","family":"Sivakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui Qi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9401-4918","authenticated-orcid":false,"given":"Zachary W","family":"Ulissi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2020,12,29]]},"reference":[{"key":"mlstabcc44bib1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1021\/nl5005674","volume":"14","author":"Artrith","year":"2014","journal-title":"Nano Lett."},{"key":"mlstabcc44bib2","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1021\/acs.jpclett.5b01456","volume":"6","author":"Rupp","year":"2015","journal-title":"J. Phys. Chem. Lett."},{"key":"mlstabcc44bib3","doi-asserted-by":"publisher","first-page":"28704","DOI":"10.1039\/C6CP05711J","volume":"18","author":"Natarajan","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstabcc44bib4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1063\/1.4960708","volume":"145","author":"Peterson","year":"2016","journal-title":"J. Chem. Phys."},{"key":"mlstabcc44bib5","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1063\/1.4966192","volume":"145","author":"Behler","year":"2016","journal-title":"J. Chem. Phys."},{"key":"mlstabcc44bib6","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1016\/j.cpc.2016.05.010","volume":"207","author":"Khorshidi","year":"2016","journal-title":"Comput. Phys. Commun."},{"key":"mlstabcc44bib7","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.104.136403","volume":"104","author":"Bart\u00f3k","year":"2010","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcc44bib8","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1021\/acs.jpca.9b08723","volume":"124","author":"Zuo","year":"2020"},{"key":"mlstabcc44bib9","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1002\/aenm.201903242","volume":"10","author":"Chen","year":"2020","journal-title":"Adv. Energy Mater."},{"key":"mlstabcc44bib10","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1063\/1.5126336","volume":"152","author":"Mueller","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstabcc44bib11","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1088\/2515-7639\/ab084b","volume":"2","author":"Schleder","year":"2019","journal-title":"J. Phys.: Mater."},{"key":"mlstabcc44bib12","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41524-020-0283-z","volume":"6","author":"Vandermause","year":"2020","journal-title":"npj Comput. Mater."},{"key":"mlstabcc44bib13","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.225701","volume":"122","author":"Jinnouchi","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcc44bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.156001","volume":"122","author":"Garrido Torres","year":"2019","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcc44bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.100.104103","volume":"100","author":"Del R\u00edo","year":"2019"},{"key":"mlstabcc44bib16","author":"Settles","year":"2010"},{"key":"mlstabcc44bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.146401","volume":"98","author":"Behler","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcc44bib18","article-title":"AMPtorch: Atomistic Machine Learning Package (AMP) - PyTorch","author":"Shuaibi","year":"2020"},{"key":"mlstabcc44bib19","article-title":"Physics enabled convergence of offline active learning with machine learning potentials","author":"Shuaibi","year":"2020"},{"key":"mlstabcc44bib20","author":"Loshchilov","year":"2019"},{"key":"mlstabcc44bib21","author":"Fey","year":"2019"},{"key":"mlstabcc44bib22","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"mlstabcc44bib23","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1002\/qua.24927","volume":"115","author":"Bart\u00f5k","year":"2015","journal-title":"J. Quantum Chem."},{"key":"mlstabcc44bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/acs.jctc.9b00805","volume":"16","author":"Schran","year":"2020"},{"key":"mlstabcc44bib25","article-title":"Integrating physics-based modeling with machine learning: a survey","author":"Willard","year":"2020"},{"key":"mlstabcc44bib26","author":"Karpatne","year":"2017"},{"key":"mlstabcc44bib27","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1021\/acs.jctc.5b00099","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"mlstabcc44bib28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1557\/mrc.2019.80","volume":"9","author":"Zhu","year":"2019","journal-title":"MRS Commun."},{"key":"mlstabcc44bib29","article-title":"Sgdr: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"mlstabcc44bib30","doi-asserted-by":"publisher","DOI":"10.1039\/C7CP00375G","volume":"19","author":"Peterson","year":"2017","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstabcc44bib31","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1038\/s41524-020-00367-7","volume":"6","author":"Sivaraman","year":"2020","journal-title":"npj Comput. Mater."},{"key":"mlstabcc44bib32","article-title":"The MLIP package: Moment tensor potentials with MPI and active learning","author":"Novikov","year":"2020"},{"key":"mlstabcc44bib33","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1021\/acs.jctc.0c00362","volume":"16","author":"Rossi","year":"2020","journal-title":"J. Chem. Theory Comput."},{"key":"mlstabcc44bib34","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1088\/2632-2153\/ab7e1a","volume":"1","author":"Tran","year":"2020"},{"key":"mlstabcc44bib35","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1103\/PhysRevB.48.13115","volume":"48","author":"Kresse","year":"1993","journal-title":"Phys. Rev. B"},{"key":"mlstabcc44bib36","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/0927-0256(96)00008-0","volume":"6","author":"Kresse","year":"1996","journal-title":"Comput. Mater. Sci."},{"key":"mlstabcc44bib37","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1088\/0953-8984\/21\/39\/395502","volume":"21","author":"Giannozzi","year":"2009"},{"key":"mlstabcc44bib38","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1063\/1.1329672","volume":"113","author":"Henkelman","year":"2000","journal-title":"J. Chem. Phys."},{"key":"mlstabcc44bib39","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1063\/1.1323224","volume":"113","author":"Henkelman","year":"2000","journal-title":"J. Chem. Phys."},{"key":"mlstabcc44bib40","author":"Ang","year":"2020","journal-title":"ChemRxiv"},{"key":"mlstabcc44bib41","article-title":"The open catalyst 2020 (oc20) dataset and community challenges","author":"Chanussot","year":"2020"},{"key":"mlstabcc44bib42","article-title":"Adversarial training and provable robustness: a tale of two objectives","author":"Fan","year":"2020"},{"key":"mlstabcc44bib43","article-title":"Certified defenses for data poisoning attacks","author":"Steinhardt","year":"2017"},{"key":"mlstabcc44bib44","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1088\/1361-648x\/aa680e","volume":"29","author":"Hjorth Larsen","year":"2017","journal-title":"J. Phys. Conden. Matter"},{"key":"mlstabcc44bib45","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1103\/PhysRevLett.77.3865","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"mlstabcc44bib46","first-page":"446","volume":"81","author":"Garrity","year":"2014"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/ampdf","content-type":"application\/pdf","content-version":"am","intended-application":"unspecified"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:25:28Z","timestamp":1642551928000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abcc44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,29]]},"references-count":46,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,12,29]]},"published-print":{"date-parts":[[2021,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abcc44","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,29]]},"assertion":[{"value":"Enabling robust offline active learning for machine learning potentials using simple physics-based priors","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":"2020-08-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-11-19","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}