Physics and chemistry from parsimonious representations: image analysis via invariant variational autoencoders
Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenome...
Saved in:
| Published in: | npj computational materials Vol. 10; no. 1; pp. 183 - 19 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
London
Nature Publishing Group UK
14.08.2024
Nature Publishing Group Nature Portfolio |
| Subjects: | |
| ISSN: | 2057-3960, 2057-3960 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenomena from the data, such as manifestations of symmetry breaking phenomena in electron and scanning tunneling microscopy images, or variability of the nanoparticles. Variational autoencoders (VAEs) are emerging as a powerful paradigm for the unsupervised data analysis, allowing to disentangle the factors of variability and discover optimal parsimonious representation. Here, we summarize recent developments in VAEs, covering the basic principles and intuition behind the VAEs. The invariant VAEs are introduced as an approach to accommodate scale and translation invariances present in imaging data and separate known factors of variations from the ones to be discovered. We further describe the opportunities enabled by the control over VAE architecture, including conditional, semi-supervised, and joint VAEs. Several case studies of VAE applications for toy models and experimental datasets in Scanning Transmission Electron Microscopy are discussed, emphasizing the deep connection between VAE and basic physical principles. Python codes and datasets discussed in this article are available at
https://github.com/saimani5/VAE-tutorials
and can be used by researchers as an application guide when applying these to their own datasets. |
|---|---|
| AbstractList | Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenomena from the data, such as manifestations of symmetry breaking phenomena in electron and scanning tunneling microscopy images, or variability of the nanoparticles. Variational autoencoders (VAEs) are emerging as a powerful paradigm for the unsupervised data analysis, allowing to disentangle the factors of variability and discover optimal parsimonious representation. Here, we summarize recent developments in VAEs, covering the basic principles and intuition behind the VAEs. The invariant VAEs are introduced as an approach to accommodate scale and translation invariances present in imaging data and separate known factors of variations from the ones to be discovered. We further describe the opportunities enabled by the control over VAE architecture, including conditional, semi-supervised, and joint VAEs. Several case studies of VAE applications for toy models and experimental datasets in Scanning Transmission Electron Microscopy are discussed, emphasizing the deep connection between VAE and basic physical principles. Python codes and datasets discussed in this article are available at https://github.com/saimani5/VAE-tutorials and can be used by researchers as an application guide when applying these to their own datasets. Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenomena from the data, such as manifestations of symmetry breaking phenomena in electron and scanning tunneling microscopy images, or variability of the nanoparticles. Variational autoencoders (VAEs) are emerging as a powerful paradigm for the unsupervised data analysis, allowing to disentangle the factors of variability and discover optimal parsimonious representation. Here, we summarize recent developments in VAEs, covering the basic principles and intuition behind the VAEs. The invariant VAEs are introduced as an approach to accommodate scale and translation invariances present in imaging data and separate known factors of variations from the ones to be discovered. We further describe the opportunities enabled by the control over VAE architecture, including conditional, semi-supervised, and joint VAEs. Several case studies of VAE applications for toy models and experimental datasets in Scanning Transmission Electron Microscopy are discussed, emphasizing the deep connection between VAE and basic physical principles. Python codes and datasets discussed in this article are available at https://github.com/saimani5/VAE-tutorials and can be used by researchers as an application guide when applying these to their own datasets. Abstract Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale structures and functionalities. This necessitates the development of the machine learning methods for discovery of physical and chemical phenomena from the data, such as manifestations of symmetry breaking phenomena in electron and scanning tunneling microscopy images, or variability of the nanoparticles. Variational autoencoders (VAEs) are emerging as a powerful paradigm for the unsupervised data analysis, allowing to disentangle the factors of variability and discover optimal parsimonious representation. Here, we summarize recent developments in VAEs, covering the basic principles and intuition behind the VAEs. The invariant VAEs are introduced as an approach to accommodate scale and translation invariances present in imaging data and separate known factors of variations from the ones to be discovered. We further describe the opportunities enabled by the control over VAE architecture, including conditional, semi-supervised, and joint VAEs. Several case studies of VAE applications for toy models and experimental datasets in Scanning Transmission Electron Microscopy are discussed, emphasizing the deep connection between VAE and basic physical principles. Python codes and datasets discussed in this article are available at https://github.com/saimani5/VAE-tutorials and can be used by researchers as an application guide when applying these to their own datasets. |
| ArticleNumber | 183 |
| Author | Ziatdinov, Maxim Liu, Yongtao Valleti, Mani Kalinin, Sergei V. |
| Author_xml | – sequence: 1 givenname: Mani surname: Valleti fullname: Valleti, Mani email: svalleti@vols.utk.edu organization: Bredesen Center for Interdisciplinary Research, University of Tennessee – sequence: 2 givenname: Maxim surname: Ziatdinov fullname: Ziatdinov, Maxim organization: Physical Sciences Division, Pacific Northwest National Laboratory – sequence: 3 givenname: Yongtao surname: Liu fullname: Liu, Yongtao organization: Center for Nanophase Materials Sciences, Oak Ridge National Laboratory – sequence: 4 givenname: Sergei V. orcidid: 0000-0001-5354-6152 surname: Kalinin fullname: Kalinin, Sergei V. email: sergei2@utk.edu organization: Physical Sciences Division, Pacific Northwest National Laboratory, Institute for Advanced Materials and Manufacturing, Department of Materials Science and Engineering, University of Tennessee |
| BackLink | https://www.osti.gov/servlets/purl/2439897$$D View this record in Osti.gov |
| BookMark | eNp9kU9v1DAQxSNUJErpF-AUwTkw_pM45oYqCpUqwQHOluNMdr3K2ovHW2m_fZ0NqIhDD6OxRr_3NOP3uroIMWBVvWXwgYHoP5JkLZcNLMV4C037orrk0KpG6A4u_nm_qq6JdgDANO-5hMsq_NieyDuqbRhrt8W9p5xO9ZTivj7YRH4fg49HqhMeEhKGbLOPgT7Vfm83WGR2LgZUP3hb-_Bgk7ch1-e-gHau7TFHDC6OmOhN9XKyM-H1n35V_br98vPmW3P__evdzef7xsm2yw0TTnZq1OC4Vm5Qup_a0SGHSSsYukFYIUdgVg-qRceZ6qHnnEvJLRsnx8RVdbf6jtHuzCGVZdPJROvNeRDTxtiUvZvRAJtQdRMTI6AUqKzSknMn-1GLoZVT8Xq3ekXK3pDzGd3WxRDQZcOl0L1WBXq_QocUfx-RstnFYyrnkxGgyxWKi7ZQ_Uq5FIkSTqa4nf8pJ-tnw8AsiZo1UQNLLYmaRcr_k_696lmRWEVU4LDB9LTVM6pH--y2Cw |
| CitedBy_id | crossref_primary_10_1016_j_chemer_2024_126197 crossref_primary_10_1002_aidi_202500063 crossref_primary_10_1063_5_0222403 crossref_primary_10_1039_D5DD00033E crossref_primary_10_1016_j_ijpharm_2025_126046 crossref_primary_10_69761_udpm2547 crossref_primary_10_1016_j_nantod_2025_102766 crossref_primary_10_1021_acsnano_5c04200 crossref_primary_10_1002_adma_202418927 crossref_primary_10_1038_s41524_025_01770_8 |
| Cites_doi | 10.1145/3065386 10.1063/1.4998599 10.1002/adma.201900608 10.1002/smll.202104318 10.1007/s12274-018-2141-6 10.1021/ci00057a005 10.1088/2632-2153/acb316 10.1111/j.1551-2916.2009.03240.x 10.1002/adma.202103680 10.1002/smll.202100181 10.1613/jair.614 10.1063/1.123922 10.1088/2632-2153/ac28de 10.1088/1361-6528/ac2f5b 10.1063/1.119519 10.1021/acsami.0c15085 10.1126/science.275.5304.1295 10.1016/j.matt.2021.09.024 10.1088/2632-2153/aba947 10.1038/s42256-022-00555-8 10.1002/cphc.200400212 10.1038/s41928-019-0264-8 10.7717/peerj.453 10.1093/jmicro/dfn030 10.1021/acsnano.1c09059 10.1103/PhysRevLett.86.4056 10.1002/advs.202203957 10.1103/PhysRevLett.105.197602 10.1126/sciadv.abd5084 10.1103/PhysRevLett.57.2579 10.1016/0304-3991(92)90381-S 10.1063/1.97800 10.1111/j.1365-2818.1981.tb01227.x 10.1038/nmeth.1483 10.1146/annurev.matsci.27.1.381 10.1146/annurev.matsci.28.1.101 10.1146/annurev-matsci-070616-124014 10.1002/smll.201801771 10.1038/nnano.2006.70 10.1016/S1367-5931(00)00126-5 10.1126/sciadv.aaw8989 10.1021/acsnano.3c03363 10.1561/2200000056 10.1109/5.726791 10.1021/acsnano.7b07504 10.1007/978-3-319-60801-3_27 10.1007/978-3-030-01237-3_34 10.1201/9780429243011 |
| ContentType | Journal Article |
| Copyright | UT-Battelle,LLC, Battelle Memorial Institute and Mani Valleti 2024 UT-Battelle,LLC, Battelle Memorial Institute and Mani Valleti 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: UT-Battelle,LLC, Battelle Memorial Institute and Mani Valleti 2024 – notice: UT-Battelle,LLC, Battelle Memorial Institute and Mani Valleti 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| CorporateAuthor | Pacific Northwest National Laboratory (PNNL), Richland, WA (United States) Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States) |
| CorporateAuthor_xml | – name: Pacific Northwest National Laboratory (PNNL), Richland, WA (United States) – name: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States) |
| DBID | C6C AAYXX CITATION 3V. 7X7 7XB 8FE 8FG 8FH 8FI 8FJ 8FK ABJCF ABUWG AFKRA AZQEC BBNVY BENPR BGLVJ BHPHI CCPQU D1I DWQXO FYUFA GHDGH GNUQQ HCIFZ K9. KB. LK8 M0S M7P PDBOC PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQGLB PQQKQ PQUKI PRINS OIOZB OTOTI DOA |
| DOI | 10.1038/s41524-024-01250-5 |
| DatabaseName | SpringerOpen Free (Free internet resource, activated by CARLI) CrossRef ProQuest Central (Corporate) Health & Medical Collection ProQuest Central (purchase pre-March 2016) ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Collection Hospital Premium Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest SciTech Premium Collection Technology Collection Materials Science & Engineering Database ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials - QC Biological Science Collection ProQuest Central ProQuest Technology Collection Natural Science Collection ProQuest One ProQuest Materials Science Collection ProQuest Central Korea Proquest Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Central Student SciTech Collection (ProQuest) ProQuest Health & Medical Complete (Alumni) Materials Science Database ProQuest Biological Science Collection Health & Medical Collection (Alumni) Biological Science Database Materials Science Collection Proquest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China OSTI.GOV - Hybrid OSTI.GOV DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Publicly Available Content Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Central Essentials Materials Science Collection ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest One Health & Nursing ProQuest Natural Science Collection ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) Natural Science Collection ProQuest Central Korea Biological Science Collection Materials Science Database ProQuest Central (New) ProQuest Materials Science Collection ProQuest Biological Science Collection ProQuest One Academic Eastern Edition ProQuest Hospital Collection ProQuest Technology Collection Health Research Premium Collection (Alumni) Biological Science Database ProQuest SciTech Collection ProQuest Hospital Collection (Alumni) ProQuest Health & Medical Complete ProQuest One Academic UKI Edition Materials Science & Engineering Collection ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: KB. name: Materials Science Database url: http://search.proquest.com/materialsscijournals sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2057-3960 |
| EndPage | 19 |
| ExternalDocumentID | oai_doaj_org_article_01fe76f13d0e43e7a79422c48d93b54f 2439897 10_1038_s41524_024_01250_5 |
| GrantInformation_xml | – fundername: Laboratory Directed Research and Development Program at Pacific Northwest National Laboratory, a multiprogram national laboratory operated by Battelle for the U.S. Department of Energy. – fundername: Center for 3D Ferroelectric Microelectronics (3DFeM), an Energy Frontier Research Center funded by the U.S. Department of Energy (DOE), Office of Science, Basic Energy Sciences under Award Number DE-SC0021118. – fundername: US Department of Energy, Office of Science, Office of Basic Energy Sciences, as part of the Energy Frontier 51 Research Centers program: CSSAS—The Center for the Science of Synthesis Across Scales— under Award No.DE-SC0019288 – fundername: US Department of Energy, Office of Science, Office of Basic Energy Sciences, as part of the Energy Frontier Research Centers program: CSSAS—The Center for the Science of Synthesis Across Scales— under Award No.DE-SC0019288 |
| GroupedDBID | 0R~ 3V. 5VS 7X7 8FE 8FG 8FH 8FI 8FJ AAJSJ ABJCF ABUWG ACGFS ACSMW ADBBV ADMLS AFKRA AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS ARCSS BBNVY BCNDV BENPR BGLVJ BHPHI BPHCQ BVXVI C6C CCPQU D1I EBLON EBS FYUFA GROUPED_DOAJ HCIFZ HMCUK KB. KQ8 LK8 M7P M~E NAO NO~ OK1 PDBOC PIMPY PQQKQ PROAC RNT SNYQT UKHRP AASML AAYXX AFFHD CITATION PHGZM PHGZT PQGLB 7XB 8FK AZQEC DWQXO GNUQQ K9. PJZUB PKEHL PPXIY PQEST PQUKI PRINS OIOZB OTOTI |
| ID | FETCH-LOGICAL-c456t-13c467d90c297cb798f5dce20f970b6b3a34d01a9b75ec217808222442a1dfc13 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001291740800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2057-3960 |
| IngestDate | Tue Oct 14 19:03:14 EDT 2025 Mon Dec 08 04:30:17 EST 2025 Sat Nov 29 14:47:01 EST 2025 Sat Nov 29 02:57:05 EST 2025 Tue Nov 18 22:43:11 EST 2025 Fri Feb 21 02:40:23 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c456t-13c467d90c297cb798f5dce20f970b6b3a34d01a9b75ec217808222442a1dfc13 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF) USDOE Laboratory Directed Research and Development (LDRD) Program None AC05-00OR22725; SC0019288 |
| ORCID | 0000-0001-5354-6152 0000000153546152 0000000301521783 |
| OpenAccessLink | https://doaj.org/article/01fe76f13d0e43e7a79422c48d93b54f |
| PQID | 3092977235 |
| PQPubID | 2041924 |
| PageCount | 19 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_01fe76f13d0e43e7a79422c48d93b54f osti_scitechconnect_2439897 proquest_journals_3092977235 crossref_citationtrail_10_1038_s41524_024_01250_5 crossref_primary_10_1038_s41524_024_01250_5 springer_journals_10_1038_s41524_024_01250_5 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-08-14 |
| PublicationDateYYYYMMDD | 2024-08-14 |
| PublicationDate_xml | – month: 08 year: 2024 text: 2024-08-14 day: 14 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: United States |
| PublicationTitle | npj computational materials |
| PublicationTitleAbbrev | npj Comput Mater |
| PublicationYear | 2024 |
| Publisher | Nature Publishing Group UK Nature Publishing Group Nature Portfolio |
| Publisher_xml | – name: Nature Publishing Group UK – name: Nature Publishing Group – name: Nature Portfolio |
| References | Noy, Vezenov, Lieber (CR14) 1997; 27 Pennycook, Varela, Lupini, Oxley, Chisholm (CR17) 2009; 58 Grutter, Liu, LeBlanc, Durig (CR12) 1997; 71 CR36 CR35 CR34 CR33 CR31 Dyck (CR56) 2018; 14 Hui, Lanza (CR7) 2019; 2 Roccapriore, Ziatdinov, Cho, Hachtel, Kalinin (CR39) 2021; 17 CR4 Lecun, Bottou, Bengio, Haffner (CR41) 1998; 86 van Zuylen (CR1) 1981; 121 Gruverman, Auciello, Tokumoto (CR15) 1998; 28 Martin, Wickramasinghe (CR13) 1987; 50 Wen, Cherukara, Holt (CR6) 2019; 49 Liu, Ziatdinov, Kalinin (CR46) 2021; 16 Kalinin, Steffes, Liu, Huey, Ziatdinov (CR45) 2021; 33 Opitz, Maclin (CR26) 1999; 11 Liu, Kelley, Funakubo, Kalinin, Ziatdinov (CR29) 2022; 9 Kalinin, Dyck, Jesse, Ziatdinov (CR52) 2021; 7 Wang, Skaanvik, Xiong, Wang, Dong (CR5) 2021; 4 Krenn, Häse, Nigam, Friederich, Aspuru-Guzik (CR44) 2020; 1 Ntziachristos (CR2) 2010; 7 Fan (CR3) 2019; 31 Ziatdinov, Ghosh, Wong, Kalinin (CR40) 2022; 4 Kingma, Welling (CR32) 2019; 12 Clausen-Schaumann, Seitz, Krautbauer, Gaub (CR21) 2000; 4 Liu (CR30) 2023; 17 Binnig, Rohrer (CR9) 1982; 55 Ziatdinov (CR53) 2019; 5 Kalinin, Kelley, Vasudevan, Ziatdinov (CR38) 2021; 13 Van der Walt (CR24) 2014; 2 Duvenaud (CR42) 2015; 28 Browning (CR20) 1999; 74 CR51 Sohlberg, Rashkeev, Borisevich, Pennycook, Pantelides (CR18) 2004; 5 CR50 Dyck, Kim, Kalinin, Jesse (CR55) 2018; 11 Chisholm, Luo, Oxley, Pantelides, Lee (CR19) 2010; 105 Rief, Oesterhelt, Heymann, Gaub (CR22) 1997; 275 Balke, Bdikin, Kalinin, Kholkin (CR23) 2009; 92 Dyck, Kim, Kalinin, Jesse (CR54) 2017; 111 Liu, Proksch, Wong, Ziatdinov, Kalinin (CR49) 2021; 33 Liu (CR48) 2021; 2 Kim (CR16) 2001; 86 de Haan, Cohen, Welling (CR37) 2020; 33 Biswas, Vasudevan, Ziatdinov, Kalinin (CR58) 2023; 4 Ziatdinov (CR57) 2017; 11 CR28 CR27 Weininger (CR43) 1988; 28 Gerber, Lang (CR8) 2006; 1 Valleti, Ignatans, Kalinin, Tileli (CR47) 2022; 18 Asenjo, Gomezrodriguez, Baro (CR11) 1992; 42 Stroscio, Feenstra, Fein (CR10) 1986; 57 Krizhevsky, Sutskever, Hinton (CR25) 2017; 60 SJ Pennycook (1250_CR17) 2009; 58 Y Martin (1250_CR13) 1987; 50 V Ntziachristos (1250_CR2) 2010; 7 D Weininger (1250_CR43) 1988; 28 C Gerber (1250_CR8) 2006; 1 H Clausen-Schaumann (1250_CR21) 2000; 4 KM Roccapriore (1250_CR39) 2021; 17 S Van der Walt (1250_CR24) 2014; 2 DK Duvenaud (1250_CR42) 2015; 28 SV Kalinin (1250_CR38) 2021; 13 M Krenn (1250_CR44) 2020; 1 A Krizhevsky (1250_CR25) 2017; 60 M Ziatdinov (1250_CR53) 2019; 5 H Wen (1250_CR6) 2019; 49 Y Liu (1250_CR30) 2023; 17 Y Liu (1250_CR49) 2021; 33 ND Browning (1250_CR20) 1999; 74 P Grutter (1250_CR12) 1997; 71 P de Haan (1250_CR37) 2020; 33 D Opitz (1250_CR26) 1999; 11 1250_CR50 1250_CR51 1250_CR4 M Ziatdinov (1250_CR57) 2017; 11 A Noy (1250_CR14) 1997; 27 J van Zuylen (1250_CR1) 1981; 121 SMP Valleti (1250_CR47) 2022; 18 K Sohlberg (1250_CR18) 2004; 5 O Dyck (1250_CR54) 2017; 111 Y Lecun (1250_CR41) 1998; 86 A Gruverman (1250_CR15) 1998; 28 SV Kalinin (1250_CR45) 2021; 33 Y Liu (1250_CR29) 2022; 9 Y Liu (1250_CR48) 2021; 2 A Asenjo (1250_CR11) 1992; 42 JA Stroscio (1250_CR10) 1986; 57 O Dyck (1250_CR55) 2018; 11 DP Kingma (1250_CR32) 2019; 12 O Dyck (1250_CR56) 2018; 14 N Balke (1250_CR23) 2009; 92 1250_CR27 MF Chisholm (1250_CR19) 2010; 105 1250_CR28 M Rief (1250_CR22) 1997; 275 Y Liu (1250_CR46) 2021; 16 A Biswas (1250_CR58) 2023; 4 M Kim (1250_CR16) 2001; 86 G Binnig (1250_CR9) 1982; 55 M Ziatdinov (1250_CR40) 2022; 4 F Hui (1250_CR7) 2019; 2 1250_CR31 1250_CR34 1250_CR33 1250_CR36 1250_CR35 Z Fan (1250_CR3) 2019; 31 Y Wang (1250_CR5) 2021; 4 SV Kalinin (1250_CR52) 2021; 7 |
| References_xml | – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: CR25 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 – volume: 111 start-page: 113104 year: 2017 ident: CR54 article-title: Placing single atoms in graphene with a scanning transmission electron microscope publication-title: Appl. Phys. Lett. doi: 10.1063/1.4998599 – volume: 31 year: 2019 ident: CR3 article-title: In situ transmission electron microscopy for energy materials and devices publication-title: Adv. Mater. doi: 10.1002/adma.201900608 – ident: CR4 – ident: CR51 – volume: 18 start-page: 2104318 year: 2022 ident: CR47 article-title: Decoding the mechanisms of phase transitions from in situ microscopy observations publication-title: Small doi: 10.1002/smll.202104318 – volume: 11 start-page: 6217 year: 2018 end-page: 6226 ident: CR55 article-title: E-beam manipulation of Si atoms on graphene edges with an aberration-corrected scanning transmission electron microscope publication-title: Nano Res. doi: 10.1007/s12274-018-2141-6 – volume: 55 start-page: 726 year: 1982 end-page: 735 ident: CR9 article-title: Scanning tunneling microscopy publication-title: Helvetica Phys. Acta – ident: CR35 – volume: 28 start-page: 31 year: 1988 end-page: 36 ident: CR43 article-title: SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules publication-title: J. Chem. Inf. Comput. Sci. doi: 10.1021/ci00057a005 – volume: 4 start-page: 015011 year: 2023 ident: CR58 article-title: Optimizing training trajectories in variational autoencoders via latent Bayesian optimization approach publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/acb316 – volume: 92 start-page: 1629 year: 2009 end-page: 1647 ident: CR23 article-title: Electromechanical imaging and spectroscopy of ferroelectric and piezoelectric materials: state of the art and prospects for the future publication-title: J. Am. Ceram. Soc. doi: 10.1111/j.1551-2916.2009.03240.x – volume: 33 start-page: 2103680 year: 2021 ident: CR49 article-title: Disentangling ferroelectric wall dynamics and identification of pinning mechanisms via deep learning publication-title: Adv. Mater. doi: 10.1002/adma.202103680 – volume: 17 start-page: 2100181 year: 2021 ident: CR39 article-title: Predictability of localized plasmonic responses in nanoparticle assemblies publication-title: Small doi: 10.1002/smll.202100181 – volume: 11 start-page: 169 year: 1999 end-page: 198 ident: CR26 article-title: Popular ensemble methods: an empirical study publication-title: J. Artif. Intell. Res. doi: 10.1613/jair.614 – ident: CR50 – volume: 74 start-page: 2638 year: 1999 end-page: 2640 ident: CR20 article-title: The influence of atomic structure on the formation of electrical barriers at grain boundaries in SrTiO3 publication-title: Appl. Phys. Lett. doi: 10.1063/1.123922 – volume: 2 start-page: 045028 year: 2021 ident: CR48 article-title: Decoding the shift-invariant data: applications for band-excitation scanning probe microscopy publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/ac28de – volume: 33 start-page: 055707 year: 2021 ident: CR45 article-title: Disentangling ferroelectric domain wall geometries and pathways in dynamic piezoresponse force microscopy via unsupervised machine learning publication-title: Nanotechnology doi: 10.1088/1361-6528/ac2f5b – ident: CR36 – volume: 71 start-page: 279 year: 1997 end-page: 281 ident: CR12 article-title: Magnetic dissipation force microscopy publication-title: Appl. Phys. Lett. doi: 10.1063/1.119519 – volume: 13 start-page: 1693 year: 2021 end-page: 1703 ident: CR38 article-title: Toward decoding the relationship between domain structure and functionality in ferroelectrics via hidden latent variables publication-title: ACS Appl. Mater. Interfaces doi: 10.1021/acsami.0c15085 – volume: 275 start-page: 1295 year: 1997 end-page: 1297 ident: CR22 article-title: Single molecule force spectroscopy on polysaccharides by atomic force microscopy publication-title: Science doi: 10.1126/science.275.5304.1295 – volume: 4 start-page: 3483 year: 2021 end-page: 3514 ident: CR5 article-title: Scanning probe microscopy for electrocatalysis publication-title: Matter doi: 10.1016/j.matt.2021.09.024 – volume: 1 start-page: 045024 year: 2020 ident: CR44 article-title: Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/aba947 – volume: 4 start-page: 1101 year: 2022 end-page: 1112 ident: CR40 article-title: AtomAI framework for deep learning analysis of image and spectroscopy data in electron and scanning probe microscopy publication-title: Nat. Mach. Intell. doi: 10.1038/s42256-022-00555-8 – volume: 5 start-page: 1893 year: 2004 end-page: 1897 ident: CR18 article-title: Origin of anomalous Pt-Pt distances in the Pt/alumina catalytic system publication-title: Chemphyschem doi: 10.1002/cphc.200400212 – volume: 2 start-page: 221 year: 2019 end-page: 229 ident: CR7 article-title: Scanning probe microscopy for advanced nanoelectronics publication-title: Nat. Electron. doi: 10.1038/s41928-019-0264-8 – volume: 28 start-page: 2224 year: 2015 end-page: 2232 ident: CR42 article-title: Convolutional networks on graphs for learning molecular fingerprints publication-title: Adv. Neural Inf. Process. Syst – volume: 2 start-page: e453 year: 2014 ident: CR24 article-title: scikit-image: image processing in Python publication-title: PeerJ doi: 10.7717/peerj.453 – ident: CR33 – volume: 58 start-page: 87 year: 2009 end-page: 97 ident: CR17 article-title: Atomic-resolution spectroscopic imaging: past, present and future publication-title: J. Electron Microsc. doi: 10.1093/jmicro/dfn030 – volume: 16 start-page: 1250 year: 2021 end-page: 1259 ident: CR46 article-title: Exploring causal physical mechanisms via non-gaussian linear models and deep kernel learning: applications for ferroelectric domain structures publication-title: ACS Nano doi: 10.1021/acsnano.1c09059 – volume: 86 start-page: 4056 year: 2001 end-page: 4059 ident: CR16 article-title: Nonstoichiometry and the electrical activity of grain boundaries in SrTiO3 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.86.4056 – ident: CR27 – volume: 33 start-page: 3636 year: 2020 end-page: 3646 ident: CR37 article-title: Natural graph networks publication-title: Adv. Neural Inf. Process. Syst. – volume: 9 start-page: 2203957 year: 2022 ident: CR29 article-title: Exploring physics of ferroelectric domain walls in real time: deep learning enabled scanning probe microscopy publication-title: Adv. Sci. doi: 10.1002/advs.202203957 – volume: 105 start-page: 197602 year: 2010 ident: CR19 article-title: Atomic-scale compensation phenomena at polar interfaces publication-title: Phys. Rev. Lett doi: 10.1103/PhysRevLett.105.197602 – volume: 7 year: 2021 ident: CR52 article-title: Exploring order parameters and dynamic processes in disordered systems via variational autoencoders publication-title: Sci. Adv. doi: 10.1126/sciadv.abd5084 – volume: 57 start-page: 2579 year: 1986 end-page: 2582 ident: CR10 article-title: Electronic-structure of the Si(111)2x1 surface by scanning-tunneling microscopy publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.57.2579 – volume: 42 start-page: 933 year: 1992 end-page: 939 ident: CR11 article-title: Current imaging tunneling spectroscopy of metallic deposits on silicon publication-title: Ultramicroscopy doi: 10.1016/0304-3991(92)90381-S – volume: 50 start-page: 1455 year: 1987 end-page: 1457 ident: CR13 article-title: Magnetic imaging by force microscopy with 1000-A resolution publication-title: Appl. Phys. Lett. doi: 10.1063/1.97800 – volume: 121 start-page: 309 year: 1981 end-page: 328 ident: CR1 article-title: The microscopes of Antoni van Leeuwenhoek publication-title: J. Microsc. doi: 10.1111/j.1365-2818.1981.tb01227.x – volume: 7 start-page: 603 year: 2010 end-page: 614 ident: CR2 article-title: Going deeper than microscopy: the optical imaging frontier in biology publication-title: Nat. Methods doi: 10.1038/nmeth.1483 – ident: CR31 – volume: 27 start-page: 381 year: 1997 end-page: 421 ident: CR14 article-title: Chemical force microscopy publication-title: Annu. Rev. Mater. Sci. doi: 10.1146/annurev.matsci.27.1.381 – volume: 28 start-page: 101 year: 1998 end-page: 123 ident: CR15 article-title: Imaging and control of domain structures in ferroelectric thin films via scanning force microscopy publication-title: Annu. Rev. Mater. Sci. doi: 10.1146/annurev.matsci.28.1.101 – volume: 49 start-page: 389 year: 2019 end-page: 415 ident: CR6 article-title: Time-resolved X-ray microscopy for materials science publication-title: Annu. Rev. Mater. Res. doi: 10.1146/annurev-matsci-070616-124014 – ident: CR34 – volume: 14 year: 2018 ident: CR56 article-title: Building structures atom by atom via electron beam manipulation publication-title: Small doi: 10.1002/smll.201801771 – volume: 1 start-page: 3 year: 2006 end-page: 5 ident: CR8 article-title: How the doors to the nanoworld were opened publication-title: Nat. Nanotechnol. doi: 10.1038/nnano.2006.70 – volume: 4 start-page: 524 year: 2000 end-page: 530 ident: CR21 article-title: Force spectroscopy with single bio-molecules publication-title: Curr. Opin. Chem. Biol. doi: 10.1016/S1367-5931(00)00126-5 – volume: 5 year: 2019 ident: CR53 article-title: Building and exploring libraries of atomic defects in graphene: Scanning transmission electron and scanning tunneling microscopy study publication-title: Sci. Adv. doi: 10.1126/sciadv.aaw8989 – volume: 17 start-page: 9647 year: 2023 end-page: 9657 ident: CR30 article-title: Disentangling electronic transport and hysteresis at individual grain boundaries in hybrid perovskites via automated scanning probe microscopy publication-title: ACS Nano doi: 10.1021/acsnano.3c03363 – volume: 12 start-page: 307 year: 2019 end-page: 392 ident: CR32 article-title: An introduction to variational autoencoders publication-title: Found. Trends® Mach. Learn. doi: 10.1561/2200000056 – volume: 86 start-page: 2278 year: 1998 end-page: 2324 ident: CR41 article-title: Gradient-based learning applied to document recognition publication-title: Proc. IEEE doi: 10.1109/5.726791 – ident: CR28 – volume: 11 start-page: 12742 year: 2017 end-page: 12752 ident: CR57 article-title: Deep learning of atomically resolved scanning transmission electron microscopy images: chemical identification and tracking local transformations publication-title: ACS Nano doi: 10.1021/acsnano.7b07504 – volume: 2 start-page: e453 year: 2014 ident: 1250_CR24 publication-title: PeerJ doi: 10.7717/peerj.453 – ident: 1250_CR36 – volume: 12 start-page: 307 year: 2019 ident: 1250_CR32 publication-title: Found. Trends® Mach. Learn. doi: 10.1561/2200000056 – volume: 17 start-page: 2100181 year: 2021 ident: 1250_CR39 publication-title: Small doi: 10.1002/smll.202100181 – volume: 1 start-page: 3 year: 2006 ident: 1250_CR8 publication-title: Nat. Nanotechnol. doi: 10.1038/nnano.2006.70 – volume: 71 start-page: 279 year: 1997 ident: 1250_CR12 publication-title: Appl. Phys. Lett. doi: 10.1063/1.119519 – volume: 5 year: 2019 ident: 1250_CR53 publication-title: Sci. Adv. doi: 10.1126/sciadv.aaw8989 – volume: 1 start-page: 045024 year: 2020 ident: 1250_CR44 publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/aba947 – volume: 105 start-page: 197602 year: 2010 ident: 1250_CR19 publication-title: Phys. Rev. Lett doi: 10.1103/PhysRevLett.105.197602 – volume: 86 start-page: 2278 year: 1998 ident: 1250_CR41 publication-title: Proc. IEEE doi: 10.1109/5.726791 – volume: 2 start-page: 045028 year: 2021 ident: 1250_CR48 publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/ac28de – volume: 14 year: 2018 ident: 1250_CR56 publication-title: Small doi: 10.1002/smll.201801771 – volume: 7 start-page: 603 year: 2010 ident: 1250_CR2 publication-title: Nat. Methods doi: 10.1038/nmeth.1483 – volume: 31 year: 2019 ident: 1250_CR3 publication-title: Adv. Mater. doi: 10.1002/adma.201900608 – volume: 275 start-page: 1295 year: 1997 ident: 1250_CR22 publication-title: Science doi: 10.1126/science.275.5304.1295 – volume: 74 start-page: 2638 year: 1999 ident: 1250_CR20 publication-title: Appl. Phys. Lett. doi: 10.1063/1.123922 – ident: 1250_CR34 doi: 10.1007/978-3-319-60801-3_27 – volume: 86 start-page: 4056 year: 2001 ident: 1250_CR16 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.86.4056 – ident: 1250_CR33 – volume: 60 start-page: 84 year: 2017 ident: 1250_CR25 publication-title: Commun. ACM doi: 10.1145/3065386 – volume: 4 start-page: 015011 year: 2023 ident: 1250_CR58 publication-title: Mach. Learn. Sci. Technol. doi: 10.1088/2632-2153/acb316 – volume: 55 start-page: 726 year: 1982 ident: 1250_CR9 publication-title: Helvetica Phys. Acta – volume: 7 year: 2021 ident: 1250_CR52 publication-title: Sci. Adv. doi: 10.1126/sciadv.abd5084 – volume: 18 start-page: 2104318 year: 2022 ident: 1250_CR47 publication-title: Small doi: 10.1002/smll.202104318 – volume: 11 start-page: 169 year: 1999 ident: 1250_CR26 publication-title: J. Artif. Intell. Res. doi: 10.1613/jair.614 – volume: 49 start-page: 389 year: 2019 ident: 1250_CR6 publication-title: Annu. Rev. Mater. Res. doi: 10.1146/annurev-matsci-070616-124014 – volume: 111 start-page: 113104 year: 2017 ident: 1250_CR54 publication-title: Appl. Phys. Lett. doi: 10.1063/1.4998599 – volume: 92 start-page: 1629 year: 2009 ident: 1250_CR23 publication-title: J. Am. Ceram. Soc. doi: 10.1111/j.1551-2916.2009.03240.x – volume: 33 start-page: 055707 year: 2021 ident: 1250_CR45 publication-title: Nanotechnology doi: 10.1088/1361-6528/ac2f5b – volume: 33 start-page: 2103680 year: 2021 ident: 1250_CR49 publication-title: Adv. Mater. doi: 10.1002/adma.202103680 – volume: 9 start-page: 2203957 year: 2022 ident: 1250_CR29 publication-title: Adv. Sci. doi: 10.1002/advs.202203957 – volume: 28 start-page: 2224 year: 2015 ident: 1250_CR42 publication-title: Adv. Neural Inf. Process. Syst – volume: 50 start-page: 1455 year: 1987 ident: 1250_CR13 publication-title: Appl. Phys. Lett. doi: 10.1063/1.97800 – ident: 1250_CR27 doi: 10.1007/978-3-030-01237-3_34 – volume: 4 start-page: 524 year: 2000 ident: 1250_CR21 publication-title: Curr. Opin. Chem. Biol. doi: 10.1016/S1367-5931(00)00126-5 – volume: 121 start-page: 309 year: 1981 ident: 1250_CR1 publication-title: J. Microsc. doi: 10.1111/j.1365-2818.1981.tb01227.x – ident: 1250_CR28 – volume: 33 start-page: 3636 year: 2020 ident: 1250_CR37 publication-title: Adv. Neural Inf. Process. Syst. – ident: 1250_CR50 – volume: 2 start-page: 221 year: 2019 ident: 1250_CR7 publication-title: Nat. Electron. doi: 10.1038/s41928-019-0264-8 – volume: 13 start-page: 1693 year: 2021 ident: 1250_CR38 publication-title: ACS Appl. Mater. Interfaces doi: 10.1021/acsami.0c15085 – ident: 1250_CR31 – volume: 4 start-page: 3483 year: 2021 ident: 1250_CR5 publication-title: Matter doi: 10.1016/j.matt.2021.09.024 – volume: 42 start-page: 933 year: 1992 ident: 1250_CR11 publication-title: Ultramicroscopy doi: 10.1016/0304-3991(92)90381-S – ident: 1250_CR35 – volume: 4 start-page: 1101 year: 2022 ident: 1250_CR40 publication-title: Nat. Mach. Intell. doi: 10.1038/s42256-022-00555-8 – volume: 58 start-page: 87 year: 2009 ident: 1250_CR17 publication-title: J. Electron Microsc. doi: 10.1093/jmicro/dfn030 – ident: 1250_CR4 doi: 10.1201/9780429243011 – volume: 27 start-page: 381 year: 1997 ident: 1250_CR14 publication-title: Annu. Rev. Mater. Sci. doi: 10.1146/annurev.matsci.27.1.381 – volume: 17 start-page: 9647 year: 2023 ident: 1250_CR30 publication-title: ACS Nano doi: 10.1021/acsnano.3c03363 – volume: 28 start-page: 101 year: 1998 ident: 1250_CR15 publication-title: Annu. Rev. Mater. Sci. doi: 10.1146/annurev.matsci.28.1.101 – volume: 28 start-page: 31 year: 1988 ident: 1250_CR43 publication-title: J. Chem. Inf. Comput. Sci. doi: 10.1021/ci00057a005 – volume: 11 start-page: 6217 year: 2018 ident: 1250_CR55 publication-title: Nano Res. doi: 10.1007/s12274-018-2141-6 – volume: 16 start-page: 1250 year: 2021 ident: 1250_CR46 publication-title: ACS Nano doi: 10.1021/acsnano.1c09059 – volume: 57 start-page: 2579 year: 1986 ident: 1250_CR10 publication-title: Phys. Rev. Lett. doi: 10.1103/PhysRevLett.57.2579 – volume: 11 start-page: 12742 year: 2017 ident: 1250_CR57 publication-title: ACS Nano doi: 10.1021/acsnano.7b07504 – volume: 5 start-page: 1893 year: 2004 ident: 1250_CR18 publication-title: Chemphyschem doi: 10.1002/cphc.200400212 – ident: 1250_CR51 |
| SSID | ssj0001928240 |
| Score | 2.3172483 |
| Snippet | Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and mesoscale... Abstract Electron, optical, and scanning probe microscopy methods are generating ever increasing volume of image data containing information on atomic and... |
| SourceID | doaj osti proquest crossref springer |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 183 |
| SubjectTerms | 639/301 639/925/918 Broken symmetry Characterization and Evaluation of Materials Chemistry and Materials Science Computational Intelligence Data analysis Datasets graphene Image analysis Image processing Invariants Machine learning MATERIALS SCIENCE Mathematical and Computational Engineering Mathematical and Computational Physics Mathematical Modeling and Industrial Mathematics Microscopy Nanoparticles Representations Scanning probe microscopy Scanning transmission electron microscopy Scanning tunneling microscopy Theoretical Transmission electron microscopy |
| SummonAdditionalLinks | – databaseName: Health & Medical Collection dbid: 7X7 link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELagcIAD5SlCW-QDN7DqV9YOF0QRVU8VB5D2Zjl2jFaCZNls9_cz4zhdikQvHCJLiRM5mvE87PH3EfIGjKKVSXgGaZdh2tvAvEhI91K3MkYjokmZbMJcXtrlsvlSFtzGUlY528RsqOMQcI38VHFw5BAKqvrD-hdD1ijcXS0UGnfJPaTNRj03S7NfY2kgodC8nJXhyp6O6K8043jBcDirb_ijDNsPzQDT60bI-dcuaXY-54f_O-zH5FEJO-nHSU-ekDtd_5Q8_AOM8BnpczFoGKnvIw0zDxzF8yd0DekvCLXHglmacTDnM0v9-J6ufoJRgtcmeBO6W3m66neQhIPUaG6nBUfqr7YDAmdi8fRz8u3889dPF6ywMbAAQRZy1gcwqrHhAX4otKaxqY6hkzw1hreLVnmlIxe-aU3dBch0bCYL11p6EVMQ6gU56Ie-e0lo7AQojqr5wrcaOlqeECnNS_CjQTS2ImKWiQsFqhwZM364vGWurJvk6DheKEdXV-Tt9TvrCajj1t5nKOrrngiynW8Mm--uzFnomzqzSEJF3mnVGQ-2S8qgbWxUW-tUkSNUFAexCgLuBqxMClsnIcazjanI8awRrtiF0e3VoSLvZp3aP_73gF_d_rUj8kBmpbZM6GNysN1cdSfkfthtV-PmdZ4VvwHlhRMy priority: 102 providerName: ProQuest |
| Title | Physics and chemistry from parsimonious representations: image analysis via invariant variational autoencoders |
| URI | https://link.springer.com/article/10.1038/s41524-024-01250-5 https://www.proquest.com/docview/3092977235 https://www.osti.gov/servlets/purl/2439897 https://doaj.org/article/01fe76f13d0e43e7a79422c48d93b54f |
| Volume | 10 |
| WOSCitedRecordID | wos001291740800002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: DOA dateStart: 20150101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVPQU databaseName: Biological Science Database (ProQuest) customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: M7P dateStart: 20240101 isFulltext: true titleUrlDefault: http://search.proquest.com/biologicalscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: Materials Science Database customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: KB. dateStart: 20240101 isFulltext: true titleUrlDefault: http://search.proquest.com/materialsscijournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: BENPR dateStart: 20240101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Health & Medical customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: 7X7 dateStart: 20240101 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2057-3960 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001928240 issn: 2057-3960 databaseCode: PIMPY dateStart: 20240101 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwELagcIADKi-xtF35wA1C_cra5sZWrUCIVYRAWk6WY8fSVpCtmu3-fmacpGyRKBcOTqTYlkae8Tzi8TeEvAKlaETivoCwSxfKm1B4nrDcS1mLGDWPOuViE3qxMMulrXZKfWFOWA8P3C_cMeOp0bPEZWSNko32IEBCBGWilXWpEmpfpu1OMHXe-y0GbNVwS4ZJc9yhpVIFwwaEsKK8YYkyYD-81rCxbjibf5yPZrNztk8eDf4ifd_T-Zjcadon5OEOiuBT0uYsztBR30YaxgJuFC-O0AuIW4EbLWa60gxgOV42art3dPUTtAlM63FJ6Hbl6ardQvQMy03zu_9TSP3VZo2Il5j1_Ix8Ozv9evKhGMooFAG8Iyw2H0AbRsuCsDrU2ppUxtAIlqxm9ayWXqrIuLe1LpsAIYrJVb6VEp7HFLh8Tvbaddu8IDQ2HDguSzbztYKBhiWEOPMCDGDg1kwIH5fUhQFjHEtd_HD5rFsa17PBMWzIBldOyOvrORc9wsato-fIqeuRiI6dP4DMuEFm3L9kZkIOkM8OnAxEyg2YUhQ2ToBzZqyekMOR_W7Y0J2TDPxIiEQkUPBmFInf3X8n-OX_IPiAPBBZciHiV4dkb3N51RyR-2G7WXWXU3JXL_WU3JufLqov07wR4Plp_naKmawV9FQfP1fffwFOiQru |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLRJw4I0ILeADnCCqX9k4SAjxqrpqu9pDkcrJdewErQTJskkX8af4jYydpEuR6K0HDlGUxLHy-GY8tsffB_AMnaLiJTMxdrvSWBplY8NKL_eS5Ny5lLm0DGIT6XSqjo-z2Qb8GtbC-LTKwScGR-1q68fIdwTFhhxDQZG8WXyPvWqUn10dJDQ6WOwXP39gl615PfmA__c557sfj97vxb2qQGwxWPDa6xadg8uoxfpsnmaqTJwtOC2zlObjXBghHWUmy9OksBixqyB6LSU3zJWWCaz3CmzicUJHsDmbHM4-r0d1MuzCSNqvzqFC7TS-hZQx9Rt-ABon51rAIBSAuxoN-lyQ-9e8bGjudm_9bx_qNtzsA2vytrOEO7BRVHfhxh90i_egCumutiGmcsQOSnfEr7AhC-zgI2wrnxJMAtPnsCqral6R-Td0u3hbR-BCVnND5tXKoPFWLQn7bkiVmNO29tSgPj38Pny6lBd-AKOqroqHQFzB0DREQscml1hQ0dJzwRmOkYJlmYqADRjQtidj95ogX3VIChBKd7jR1G8eNzqJ4MXZPYuOiuTC0u88tM5KehrxcKJeftG9V8KyZZGOSyYcLaQoUoPemXMrlctEnsgygi0PTI3RmKcUtj73yraaYxSrsjSC7QGBuvd8jV7DL4KXA4bXl__9wI8uru0pXNs7OjzQB5Pp_hZc58GgVMzkNoza5WnxGK7aVTtvlk96myRwctno_g02nXAk |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VLUJw4FnE0gI-wAmi9SsbBwkhSruiKlqtEEi9GceO0UqQLJvtIv4av46xk3QpEr31wCGKlDhWHt-MZ5zx9wE8RaeouGcmwbQrS6RRNjHMB7mXtODOZcxlPopNZNOpOjnJZ1vwq18LE8oqe58YHbWrbZgjHwmKAzmGgiId-a4sYnYweb34ngQFqfCntZfTaCFyXP78gelb8-roAL_1M84nhx_fvks6hYHEYuAQdNgtOgqXU4t92yLLlU-dLTn1eUaLcSGMkI4ykxdZWlqM3lUUwJaSG-a8ZQL7vQLbmcCkZwDb-4fT2YfNDE-O6Yyk3UodKtSoCaOlTGjY8GXQJD03GkbRANzVaNznAt6__tHGoW9y639-abfhZhdwkzethdyBrbK6Czf-oGG8B1Usg7UNMZUjtlfAI2HlDVlg4o9wrkKpMIkMoP1qrap5Sebf0B3jZS2xC1nPDZlXa4NGXa1I3LdTrcScrupAGRrKxnfg06U88H0YVHVVPgDiSoYmI1I6NoXEhor6wBFnOEYQluVqCKzHg7YdSXvQCvmqY7GAULrFkKZhCxjS6RCen12zaClKLmy9H2B21jLQi8cD9fKL7rwVtvVlNvZMOFpKUWYGvTbnViqXiyKVfgi7AaQao7RANWxDTZZdaY7RrcqzIez1aNSdR2z0BopDeNHjeXP63zf88OLensA1hLR-fzQ93oXrPNqWSpjcg8FqeVo-gqt2vZo3y8edeRL4fNng_g1S7Hi- |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Physics+and+chemistry+from+parsimonious+representations%3A+image+analysis+via+invariant+variational+autoencoders&rft.jtitle=npj+computational+materials&rft.au=Mani+Valleti&rft.au=Maxim+Ziatdinov&rft.au=Yongtao+Liu&rft.au=Sergei+V.+Kalinin&rft.date=2024-08-14&rft.pub=Nature+Portfolio&rft.eissn=2057-3960&rft.volume=10&rft.issue=1&rft.spage=1&rft.epage=19&rft_id=info:doi/10.1038%2Fs41524-024-01250-5&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_01fe76f13d0e43e7a79422c48d93b54f |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2057-3960&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2057-3960&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2057-3960&client=summon |