{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,29]],"date-time":"2024-08-29T07:12:53Z","timestamp":1724915573614},"reference-count":32,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T00:00:00Z","timestamp":1603929600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,10,29]],"date-time":"2020-10-29T00:00:00Z","timestamp":1603929600000},"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":"publisher","id":[{"id":"10.13039\/100006151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2020,12,1]]},"abstract":"Abstract<\/jats:title>\n Interface structures in complex oxides remain an active area of condensed matter physics research, largely enabled by recent advances in scanning transmission electron microscopy (STEM). Yet the nature of the STEM contrast in which the structure is projected along the given direction precludes separation of possible structural models. Here, we utilize deep convolutional neural networks (DCNN) trained on simulated 4D STEM datasets to predict structural descriptors of interfaces. We focus on the widely studied interface between LaAlO3<\/jats:sub> and SrTiO3<\/jats:sub>, using dynamical diffraction theory and leveraging high performance computing to simulate thousands of possible 4D STEM datasets to train the DCNN to learn properties of the underlying structures on which the simulations are based. We test the DCNN on simulated data and show that it is possible (with >95% accuracy) to identify a physically rough from a chemically diffuse interface and create a DCNN regression model to predict step positions. We quantify the applicability of the model to different thicknesses and the transferability of the approach. The method shown here is general and can be applied for any inverse imaging problem where forward models are present.<\/jats:p>","DOI":"10.1088\/2632-2153\/aba32d","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T22:30:31Z","timestamp":1594074631000},"page":"04LT01","update-policy":"http:\/\/dx.doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep learning of interface structures from simulated 4D STEM data: cation intermixing vs. roughening\n \n \u2217<\/sup>\n <\/sup>"],"prefix":"10.1088","volume":"1","author":[{"given":"M P","family":"Oxley","sequence":"first","affiliation":[]},{"given":"J","family":"Yin","sequence":"additional","affiliation":[]},{"given":"N","family":"Borodinov","sequence":"additional","affiliation":[]},{"given":"S","family":"Somnath","sequence":"additional","affiliation":[]},{"given":"M","family":"Ziatdinov","sequence":"additional","affiliation":[]},{"given":"A R","family":"Lupini","sequence":"additional","affiliation":[]},{"given":"S","family":"Jesse","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4692-8579","authenticated-orcid":false,"given":"R K","family":"Vasudevan","sequence":"additional","affiliation":[]},{"given":"S V","family":"Kalinin","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2020,10,29]]},"reference":[{"key":"mlstaba32dbib1","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1038\/nature02308","article-title":"A high-mobility electron gas at the LaAlO3\/SrTiO3 heterointerface","volume":"427","author":"Ohtomo","year":"2004","journal-title":"Nature"},{"key":"mlstaba32dbib2","doi-asserted-by":"publisher","first-page":"152111","DOI":"10.1063\/1.3496440","article-title":"Conducting interfaces between band insulating oxides: the LaGaO(3)\/SrTiO(3) heterostructure","volume":"97","author":"Perna","year":"2010","journal-title":"Appl. Phys. Lett."},{"key":"mlstaba32dbib3","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/nmat1931","article-title":"Magnetic effects at the interface between non-magnetic oxides","volume":"6","author":"Brinkman","year":"2007","journal-title":"Nat. Mater."},{"key":"mlstaba32dbib4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.80.094405","article-title":"Effect of oxidation of the ultrathin Fe electrode material on the strength of magnetoelectric coupling in composite multiferroics","volume":"80","author":"Fechner","year":"2009","journal-title":"Phys. Rev. B"},{"key":"mlstaba32dbib5","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1038\/nnano.2007.412","article-title":"Carrier-mediated magnetoelectricity in complex oxide heterostructures","volume":"3","author":"Rondinelli","year":"2008","journal-title":"Nat. Nanotech."},{"key":"mlstaba32dbib6","doi-asserted-by":"publisher","first-page":"732-U4","DOI":"10.1038\/nature06817","article-title":"Improper ferroelectricity in perovskite oxide artificial superlattices","volume":"452","author":"Bousquet","year":"2008","journal-title":"Nature"},{"key":"mlstaba32dbib7","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1126\/science.1156393","article-title":"Colossal ionic conductivity at interfaces of epitaxial ZrO2: Y2O3\/SrTiO3 heterostructures","volume":"321","author":"Garcia-Barriocanal","year":"2008","journal-title":"Science"},{"key":"mlstaba32dbib8","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.105.087204","article-title":"Suppression of octahedral tilts and associated changes in electronic properties at epitaxial oxide heterostructure interfaces","volume":"105","author":"Borisevich","year":"2010","journal-title":"Phys. Rev. Lett."},{"key":"mlstaba32dbib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.105.227203","article-title":"Control of octahedral tilts and magnetic properties of perovskite oxide heterostructures by substrate symmetry","volume":"105","author":"He","year":"2010","journal-title":"Phys. Rev. Lett."},{"key":"mlstaba32dbib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.79.081405","article-title":"Oxygen octahedron reconstruction in the SrTiO(3)\/LaAlO(3) heterointerfaces investigated using aberration-corrected ultrahigh-resolution transmission electron microscopy","volume":"79","author":"Jia","year":"2009","journal-title":"Phys. Rev. B"},{"key":"mlstaba32dbib11","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.98.207601","article-title":"Ferroelectricity in asymmetric metal-ferroelectric-metal heterostructures: a combined first-principles-phenomenological approach","volume":"98","author":"Gerra","year":"2007","journal-title":"Phys. Rev. Lett."},{"key":"mlstaba32dbib12","doi-asserted-by":"publisher","first-page":"10423","DOI":"10.1021\/nn304930x","article-title":"Beyond condensed matter physics on the nanoscale: the role of ionic and electrochemical phenomena in the physical functionalities of oxide materials","volume":"6","author":"Kalinin","year":"2012","journal-title":"Acs Nano"},{"key":"mlstaba32dbib13","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1126\/science.1243098","article-title":"Functional ion defects in transition metal oxides","volume":"341","author":"Kalinin","year":"2013","journal-title":"Science"},{"key":"mlstaba32dbib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.86.140102","article-title":"Interface dipole between two metallic oxides caused by localized oxygen vacancies","volume":"86","author":"Borisevich","year":"2012","journal-title":"Phys. Rev. B"},{"key":"mlstaba32dbib15","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/nmat4058","article-title":"Direct observation of ferroelectric field effect and vacancy-controlled screening at the BiFeO3\/LaxSr1-xMnO3 interface","volume":"13","author":"Kim","year":"2014","journal-title":"Nat. Mater."},{"key":"mlstaba32dbib16","doi-asserted-by":"publisher","first-page":"1381","DOI":"10.1016\/j.susc.2011.04.035","article-title":"Cation mixing, band offsets and electric fields at LaAlO3\/SrTiO3(001) heterojunctions with variable La:Al atom ratio","volume":"605","author":"Qiao","year":"2011","journal-title":"Surf. Sci."},{"key":"mlstaba32dbib17","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1002\/adma.200801448","article-title":"Electron transfer and ionic displacements at the origin of the 2D electron gas at the LAO\/STO interface: direct measurements with atomic\u2010column spatial resolution","volume":"24","author":"Cantoni","year":"2012","journal-title":"Adv. Mater."},{"key":"mlstaba32dbib18","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.84.024203","article-title":"Spatially resolved mapping of disorder type and distribution in random systems using artificial neural network recognition","volume":"84","author":"Kumar","year":"2011","journal-title":"Phys. Rev. B"},{"key":"mlstaba32dbib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.103.157203","article-title":"Disorder identification in hysteresis data: recognition analysis of the random-bond-random-field ising model","volume":"103","author":"Ovchinnikov","year":"2009","journal-title":"Phys. Rev. Lett."},{"key":"mlstaba32dbib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-018-34525-1","article-title":"Real-time coherent diffraction inversion using deep generative networks","volume":"8","author":"Cherukara","year":"2018","journal-title":"Sci. Rep."},{"key":"mlstaba32dbib21","article-title":"Real-time sparse-sampled ptychographic imaging through deep neural networks","author":"Cherukara","year":"2020"},{"key":"mlstaba32dbib22","article-title":"Exascale deep learning for scientific inverse problems arXiv preprint","author":"Laanait","year":"2019"},{"key":"mlstaba32dbib23","first-page":"1995","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"Handbook Brain Theory Neural Netw."},{"key":"mlstaba32dbib24","doi-asserted-by":"publisher","first-page":"2351","DOI":"10.1038\/ncomms3351","article-title":"LaAlO3 stoichiometry is key to electron liquid formation at LaAlO3\/SrTiO3 interfaces","volume":"4","author":"Warusawithana","year":"2013","journal-title":"Nat. Commun."},{"key":"mlstaba32dbib25","doi-asserted-by":"publisher","DOI":"10.1063\/1.5024554","article-title":"Role of the different defects, their population and distribution in the LaAlO3\/SrTiO3 heterostructure\u2019s behavior","volume":"123","author":"Zaid","year":"2018","journal-title":"J. Appl. Phys."},{"key":"mlstaba32dbib26","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.ultramic.2014.10.011","article-title":"Modelling the inelastic scattering of fast electrons","volume":"151","author":"Allen","year":"2015","journal-title":"Ultramicroscopy"},{"key":"mlstaba32dbib27","doi-asserted-by":"publisher","first-page":"12365","DOI":"10.1021\/acsnano.5b05682","article-title":"High-T C layered ferrielectric crystals by coherent spinodal decomposition","volume":"9","author":"Susner","year":"2015","journal-title":"ACS Nano"},{"key":"mlstaba32dbib28","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/644\/1\/012032","article-title":"4D STEM: high efficiency phase contrast imaging using a fast pixelated detector","volume":"644","author":"Yang","year":"2015","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstaba32dbib29","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41524-018-0086-7","article-title":"Mapping mesoscopic phase evolution during E-beam induced transformations via deep learning of atomically resolved images","volume":"4","author":"Vasudevan","year":"2018","journal-title":"Npj Comput. Mater."},{"key":"mlstaba32dbib30","author":"Chollet","year":"2015"},{"key":"mlstaba32dbib31","first-page":"177","author":"Bottou","year":"2010"},{"key":"mlstaba32dbib32","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","author":"Simonyan","year":"2013"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/ampdf","content-type":"application\/pdf","content-version":"am","intended-application":"unspecified"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T18:53:41Z","timestamp":1642186421000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aba32d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,29]]},"references-count":32,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2020,10,29]]},"published-print":{"date-parts":[[2020,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aba32d","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,29]]},"assertion":[{"value":"Deep learning of interface structures from simulated 4D STEM data: cation intermixing vs. roughening\n \n \u2217","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":"2020-02-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-07-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-10-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}