{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T02:08:33Z","timestamp":1775095713595,"version":"3.50.1"},"reference-count":51,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T00:00:00Z","timestamp":1692576000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"NCCR-MARVEL funded by the Swiss National Science Foundation"},{"name":"European Union\u2019s Horizon 2020 research and innovation program under the Marie Sk\u0142odowska-Curie grant","award":["701647"],"award-info":[{"award-number":["701647"]}]},{"name":"European Research Council HERO Synergy Grant","award":["SYG-18 810451"],"award-info":[{"award-number":["SYG-18 810451"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>There is a growing recognition that electronic band structure is a local property of materials and devices, and there is steep growth in capabilities to collect the relevant data. New photon sources, from small-laboratory-based lasers to free electron lasers, together with focusing beam optics and advanced electron spectrometers, are beginning to enable angle-resolved photoemission spectroscopy (ARPES) in scanning mode with a spatial resolution of near to and below microns, two- to three orders of magnitude smaller than what has been typical for ARPES hitherto. The results are vast data sets inhabiting a five-dimensional subspace of the ten-dimensional space spanned by two scanning dimensions of real space, three of reciprocal space, three of spin-space, time, and energy. In this work, we demonstrate that recent developments in representational learning (self-supervised learning) combined with <jats:italic>k<\/jats:italic>-means clustering can help automate the labeling and spatial mapping of dispersion cuts, thus saving precious time relative to manual analysis, albeit with low performance. Finally, we introduce a few-shot learning (<jats:italic>k<\/jats:italic>-nearest neighbor) in representational space where we selectively choose one (<jats:italic>k<\/jats:italic> = 1) image reference for each known label and subsequently label the rest of the data with respect to the nearest reference image. This last approach demonstrates the strength of self-supervised learning to automate image analysis in ARPES in particular and can be generalized to any scientific image analysis.<\/jats:p>","DOI":"10.1088\/2632-2153\/aced7d","type":"journal-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T22:30:48Z","timestamp":1691188248000},"page":"035021","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Transfer learning application of self-supervised learning in ARPES"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1693-8082","authenticated-orcid":true,"given":"Sandy Adhitia","family":"Ekahana","sequence":"first","affiliation":[]},{"given":"Genta Indra","family":"Winata","sequence":"additional","affiliation":[]},{"given":"Y","family":"Soh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5239-6826","authenticated-orcid":true,"given":"Anna","family":"Tamai","sequence":"additional","affiliation":[]},{"given":"Radovic","family":"Milan","sequence":"additional","affiliation":[]},{"given":"Gabriel","family":"Aeppli","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Shi","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,8,21]]},"reference":[{"key":"mlstaced7dbib1","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1103\/PhysRev.105.1676","article-title":"Precision method for obtaining absolute values of atomic binding energies","volume":"105","author":"Nordling","year":"1957","journal-title":"Phys. Rev."},{"key":"mlstaced7dbib2","doi-asserted-by":"publisher","first-page":"3159","DOI":"10.1103\/PhysRevLett.70.3159","article-title":"Fermi surface and electronic structure of Nd2-xCexCuO4-d","volume":"70","author":"King","year":"1993","journal-title":"Phys. Rev. Lett."},{"key":"mlstaced7dbib3","doi-asserted-by":"publisher","first-page":"16981","DOI":"10.1103\/PhysRevB.52.R16981","article-title":"Direct observation of a narrow band near the gap edge of FeSi","volume":"52","author":"Park","year":"1995","journal-title":"Phys. Rev. B"},{"key":"mlstaced7dbib4","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1103\/PhysRevLett.78.1771","article-title":"Momentum, temperature, and doping dependence of photoemission lineshape and implications for the nature of the pairing potential in high-T-c superconducting materials","volume":"78","author":"Shen","year":"1997","journal-title":"Phys. Rev. Lett."},{"key":"mlstaced7dbib5","doi-asserted-by":"publisher","first-page":"5194","DOI":"10.1103\/PhysRevLett.85.5194","article-title":"Fermi surface, surface states, and surface reconstruction in Sr2RuO4","volume":"85","author":"Damascelli","year":"2000","journal-title":"Phys. Rev. Lett."},{"key":"mlstaced7dbib6","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.93.117003","article-title":"Coupling of the B-1g phonon to the antinodal electronic states of Bi2Sr2Ca0.92Y0.08Cu2O8+\u03b4","volume":"93","author":"Cuk","year":"2004","journal-title":"Phys. Rev. Lett."},{"key":"mlstaced7dbib7","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1038\/nmat3990","article-title":"A stable three-dimensional topological Dirac semimetal Cd3As2","volume":"13","author":"Liu","year":"2014","journal-title":"Nat. Mater."},{"key":"mlstaced7dbib8","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1126\/science.1189924","article-title":"Massive Dirac fermion on the surface of a magnetically doped topological insulator","volume":"329","author":"Chen","year":"2010","journal-title":"Science"},{"key":"mlstaced7dbib9","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1126\/science.1173034","article-title":"Experimental realization of a three-dimensional topological insulator, Bi2Te3","volume":"325","author":"Chen","year":"2009","journal-title":"Science"},{"key":"mlstaced7dbib10","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1126\/science.1245085","article-title":"Discovery of a three-dimensional topological Dirac semimetal Na3Bi","volume":"343","author":"Liu","year":"2014","journal-title":"Science"},{"key":"mlstaced7dbib11","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/aa75a1","article-title":"Observation of nodal line in non-symmorphic topological semimetal InBi","volume":"19","author":"Ekahana","year":"2017","journal-title":"New J. Phys."},{"key":"mlstaced7dbib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.95.125126","article-title":"Dirac line nodes and effect of spin-orbit coupling in the nonsymmorphic critical semimetals MSiS (M = Hf Zr)","volume":"95","author":"Chen","year":"2017","journal-title":"Phys. Rev. B"},{"key":"mlstaced7dbib13","doi-asserted-by":"publisher","first-page":"4132","DOI":"10.1038\/s41467-022-31841-z","article-title":"Fermi surface tomography","volume":"13","author":"Borisenko","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstaced7dbib14","doi-asserted-by":"publisher","DOI":"10.1063\/1.5139556","article-title":"High resolution time- and angle-resolved photoemission spectroscopy with 11 eV laser pulses","volume":"91","author":"Lee","year":"2020","journal-title":"Rev. Sci. Instrum."},{"key":"mlstaced7dbib15","doi-asserted-by":"publisher","DOI":"10.1063\/1.5081938","article-title":"Time- and angle-resolved photoemission spectroscopy of solids in the extreme ultraviolet at 500 kHz repetition rate","volume":"90","author":"Puppin","year":"2019","journal-title":"Rev. Sci. Instrum."},{"key":"mlstaced7dbib16","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1107\/S1600577517006907","article-title":"Very efficient spin polarization analysis (VESPA): new exchange scattering-based setup for spin-resolved ARPES at APE-NFFA beamline at Elettra","volume":"24","author":"Bigi","year":"2017","journal-title":"J. Synchrotron Radiat."},{"key":"mlstaced7dbib17","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/21\/40\/403001","article-title":"Spin and angle resolved photoemission on non-magnetic low-dimensional systems","volume":"21","author":"Dil","year":"2009","journal-title":"J. Phys.: Condens. Matter"},{"key":"mlstaced7dbib18","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1038\/s41578-018-0047-2","article-title":"Visualizing electronic structures of quantum materials by angle-resolved photoemission spectroscopy","volume":"3","author":"Yang","year":"2018","journal-title":"Nat. Rev. Mater."},{"key":"mlstaced7dbib19","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1038\/s42254-019-0088-5","article-title":"Angle-resolved photoemission spectroscopy and its application to topological materials","volume":"1","author":"Lv","year":"2019","journal-title":"Nat. Rev. Phys."},{"key":"mlstaced7dbib20","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1038\/s43586-022-00133-7","article-title":"Angle-resolved photoemission spectroscopy","volume":"2","author":"Zhang","year":"2022","journal-title":"Nat. Rev. Methods Primers"},{"key":"mlstaced7dbib21","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201606741","article-title":"Substrate doping effect and unusually large angle van hove singularity evolution in twisted Bi- and multilayer graphene","volume":"29","author":"Peng","year":"2017","journal-title":"Adv. Mater."},{"key":"mlstaced7dbib22","doi-asserted-by":"publisher","first-page":"2086","DOI":"10.1016\/j.scib.2020.07.032","article-title":"Persistent surface states with diminishing gap in MnBi2Te4\/Bi2Te3 superlattice antiferromagnetic topological insulator","volume":"65","author":"Xu","year":"2020","journal-title":"Sci. Bull."},{"key":"mlstaced7dbib23","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1038\/s41567-020-01041-x","article-title":"Observation of flat bands in twisted bilayer graphene","volume":"17","author":"Lisi","year":"2021","journal-title":"Nat. Phys."},{"key":"mlstaced7dbib24","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1021\/acs.nanolett.8b04534","article-title":"Microfocus laser\u2013angle-resolved photoemission on encapsulated Mono-, Bi-, and Few-Layer 1T\u2032-WTe2","volume":"19","author":"Cucchi","year":"2019","journal-title":"Nano Lett."},{"key":"mlstaced7dbib25","doi-asserted-by":"publisher","first-page":"11806","DOI":"10.1021\/acsnano.1c02902","article-title":"Revealing the chemical bonding in adatom arrays via machine learning of hyperspectral scanning tunneling spectroscopy data","volume":"15","author":"Roccapriore","year":"2021","journal-title":"ACS Nano"},{"key":"mlstaced7dbib26","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab7d2f","article-title":"Machine learning at the (sub)atomic scale: next generation scanning probe microscopy","volume":"1","author":"Gordon","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaced7dbib27","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1038\/s42005-020-0317-3","article-title":"Artificial-intelligence-driven scanning probe microscopy","volume":"3","author":"Krull","year":"2020","journal-title":"Commun. Phys."},{"key":"mlstaced7dbib28","doi-asserted-by":"publisher","first-page":"5185","DOI":"10.1021\/acsnano.8b02208","article-title":"Autonomous scanning probe microscopy in situ tip conditioning through machine learning","volume":"12","author":"Rashidi","year":"2018","journal-title":"ACS Nano"},{"key":"mlstaced7dbib29","first-page":"98","article-title":"Machine learning approach to pattern recognition in atomic force microscopy images","volume":"50","author":"Giergiel","year":"2021","journal-title":"Eur. Biophys. J. Biophys. Lett."},{"key":"mlstaced7dbib30","first-page":"p S12","article-title":"Atomic force microscopy combined with machine learning as a new approach to detect cell abnormalities: towards outeromics","volume":"vol 57","author":"Sokolov","year":"2021"},{"key":"mlstaced7dbib31","doi-asserted-by":"publisher","DOI":"10.1063\/5.0054920","article-title":"Deep learning-based statistical noise reduction for multidimensional spectral data","volume":"92","author":"Kim","year":"2021","journal-title":"Rev. Sci. Instrum."},{"key":"mlstaced7dbib32","article-title":"A machine learning route between band mapping and band structure","author":"Xian","year":"2020"},{"key":"mlstaced7dbib33","doi-asserted-by":"publisher","DOI":"10.1063\/1.5132586","article-title":"Super resolution convolutional neural network for feature extraction in spectroscopic data","volume":"91","author":"Peng","year":"2020","journal-title":"Rev. Sci. Instrum."},{"key":"mlstaced7dbib34","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abab61","article-title":"K-means-driven Gaussian process data collection for angle-resolved photoemission spectroscopy","volume":"1","author":"Melton","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaced7dbib35","article-title":"Convolutional networks for images, speech, and time-series","author":"Lecun","year":"1995"},{"key":"mlstaced7dbib36","first-page":"1027","article-title":"k-means plus plus : the advantages of careful seeding","author":"Arthur","year":"2007"},{"key":"mlstaced7dbib37","author":"Bellman","year":"1961"},{"key":"mlstaced7dbib38","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0893-6080(89)90014-2","article-title":"Neural networks and principal component analysis: learning from examples without local minima","volume":"2","author":"Baldi","year":"1989","journal-title":"Neural Netw."},{"key":"mlstaced7dbib39","first-page":"2579","article-title":"Visualizing Data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstaced7dbib40","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstaced7dbib41","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007348","article-title":"Learning unsupervised feature representations for single cell microscopy images with paired cell inpainting","volume":"15","author":"Lu","year":"2019","journal-title":"Plos Comput. Biol."},{"key":"mlstaced7dbib42","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1107\/S1600577521011139","article-title":"Machine learning denoising of high-resolution x-ray nanotomography data","volume":"29","author":"Flenner","year":"2022","journal-title":"J. Synchrotron Radiat."},{"key":"mlstaced7dbib43","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1109\/TCI.2020.3019647","article-title":"Noise2Inverse: self-supervised deep convolutional denoising for tomography","volume":"6","author":"Hendriksen","year":"2020","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"mlstaced7dbib44","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105114","article-title":"Self-supervised representation learning from 12-lead ECG data","volume":"141","author":"Mehari","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"mlstaced7dbib45","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba6f2","article-title":"Unsupervised classification of single-molecule data with autoencoders and transfer learning","volume":"1","author":"Vladyka","year":"2020","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstaced7dbib46","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00975","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"mlstaced7dbib47","first-page":"p MLR","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"mlstaced7dbib48","article-title":"Bootstrap your own latent: a new approach to self-supervised learning","author":"Grill","year":"2020"},{"key":"mlstaced7dbib49","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron","year":"2020"},{"key":"mlstaced7dbib50","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00951","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"mlstaced7dbib51","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2009.5206848","article-title":"ImageNet: a large-scale hierarchical image database","author":"Deng","year":"2009"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T12:38:34Z","timestamp":1692621514000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aced7d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,21]]},"references-count":51,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,8,21]]},"published-print":{"date-parts":[[2023,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aced7d","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,21]]},"assertion":[{"value":"Transfer learning application of self-supervised learning in ARPES","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":"2023-01-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-08-04","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-08-21","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}