No Cover Image

Journal article 26 views 4 downloads

Towards machine-learning-based on-the-fly analysis of neutron reflectometry

Anne Rentzsch Orcid Logo, Valentin Munteanu Orcid Logo, Oliver Odira Anyanor, Shreya Shah Orcid Logo, Philipp Gutfreund Orcid Logo, Rémi Perenon, Anthony Higgins Orcid Logo, Vladimir Starostin Orcid Logo, Alexander Hinderhofer Orcid Logo, Dmitry Lapkin Orcid Logo, Frank Schreiber Orcid Logo

Journal of Applied Crystallography, Volume: 59, Issue: 3

Swansea University Author: Anthony Higgins Orcid Logo

Check full text

DOI (Published version): 10.1107/s1600576726002657

Abstract

Reflectometry experiments can benefit substantially from recent advances in machine learning, enabling real-time data analysis, informed decision making during measurements, optimized experimental conditions and ultimately closed-loop experimental workflows. While most prior automation efforts have...

Full description

Published in: Journal of Applied Crystallography
ISSN: 1600-5767
Published: International Union of Crystallography (IUCr) 2026
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71909
first_indexed 2026-05-15T10:29:15Z
last_indexed 2026-05-16T05:23:14Z
id cronfa71909
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-05-15T11:34:47.8983969</datestamp><bib-version>v2</bib-version><id>71909</id><entry>2026-05-15</entry><title>Towards machine-learning-based on-the-fly analysis of neutron reflectometry</title><swanseaauthors><author><sid>4db715667aa7bdc04e87b3ab696d206a</sid><ORCID>0000-0003-2804-8164</ORCID><firstname>Anthony</firstname><surname>Higgins</surname><name>Anthony Higgins</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-15</date><deptcode>EAAS</deptcode><abstract>Reflectometry experiments can benefit substantially from recent advances in machine learning, enabling real-time data analysis, informed decision making during measurements, optimized experimental conditions and ultimately closed-loop experimental workflows. While most prior automation efforts have focused on X-ray reflectometry, neutron reflectometry can also benefit to the same extent. We report the first machine-learning-based pipeline for real-time neutron reflectometry deployed at the Institut Laue&#x2013;Langevin (ILL), Grenoble, France. The system integrates the reflectorch package into the data acquisition workflow using the IT infrastructure of the facility. This enables analysis that is two orders of magnitude faster than conventional tools, allowing real-time estimation of physical parameters with associated uncertainties and feedback through a graphical user interface. The pipeline has been successfully tested at the ILL, and can be adapted to work at other neutron facilities seeking to enable real-time feedback-driven reflectometry analysis.</abstract><type>Journal Article</type><journal>Journal of Applied Crystallography</journal><volume>59</volume><journalNumber>3</journalNumber><paginationStart/><paginationEnd/><publisher>International Union of Crystallography (IUCr)</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1600-5767</issnElectronic><keywords>neutron reflectometry; machine learning; online data analysis; experiment automation</keywords><publishedDay>1</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-06-01</publishedDate><doi>10.1107/s1600576726002657</doi><url/><notes/><college>COLLEGE NANME</college><department>Engineering and Applied Sciences School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>EAAS</DepartmentCode><institution>Swansea University</institution><apcterm>Another institution paid the OA fee</apcterm><funders>We thank the Bundesministerium fu&#xA8;r Bildung und Forschung [project VIPR 05D23VT1 (ERUM-DATA)]. We thank the Cluster of Excellence&#x2013; Machine Learning for Science, funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany&#x2019;s Excellence Strategy (EXC No. 2064/1, project No. 390727645), for support and access to computer resources. We also thank the DFG [grant No. 460248799 to DAPHNE4NFDI, HI1927/7-1 (project 557510229) and SCHR700/50-1]. The authors acknowledge the OSCARS project, which has received funding from the European Commission&#x2019;s Horizon Europe Research and Innovation programme under grant agreement No. 101129751. Oliver Anyanor thanks the UK Engineering and Physical Sciences Research Council for funding his PhD studentship (grant No. EP/W524694/1).</funders><projectreference/><lastEdited>2026-05-15T11:34:47.8983969</lastEdited><Created>2026-05-15T10:47:56.4027857</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Engineering and Applied Sciences - Biomedical Engineering</level></path><authors><author><firstname>Anne</firstname><surname>Rentzsch</surname><orcid>0009-0002-6921-0121</orcid><order>1</order></author><author><firstname>Valentin</firstname><surname>Munteanu</surname><orcid>0000-0002-5897-3863</orcid><order>2</order></author><author><firstname>Oliver Odira</firstname><surname>Anyanor</surname><order>3</order></author><author><firstname>Shreya</firstname><surname>Shah</surname><orcid>0009-0001-4330-5918</orcid><order>4</order></author><author><firstname>Philipp</firstname><surname>Gutfreund</surname><orcid>0000-0002-7412-8571</orcid><order>5</order></author><author><firstname>R&#xE9;mi</firstname><surname>Perenon</surname><order>6</order></author><author><firstname>Anthony</firstname><surname>Higgins</surname><orcid>0000-0003-2804-8164</orcid><order>7</order></author><author><firstname>Vladimir</firstname><surname>Starostin</surname><orcid>0000-0003-4533-6256</orcid><order>8</order></author><author><firstname>Alexander</firstname><surname>Hinderhofer</surname><orcid>0000-0001-8152-6386</orcid><order>9</order></author><author><firstname>Dmitry</firstname><surname>Lapkin</surname><orcid>0000-0003-0680-8740</orcid><order>10</order></author><author><firstname>Frank</firstname><surname>Schreiber</surname><orcid>0000-0003-3659-6718</orcid><order>11</order></author></authors><documents><document><filename>71909__36742__0daa3fc0e88c496d9b38e8efb1bfa8f6.pdf</filename><originalFilename>71909.VoR.pdf</originalFilename><uploaded>2026-05-15T11:29:44.8810942</uploaded><type>Output</type><contentLength>4123086</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>Published under a CC-BY 4.0 licence.</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/legalcode</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-05-15T11:34:47.8983969 v2 71909 2026-05-15 Towards machine-learning-based on-the-fly analysis of neutron reflectometry 4db715667aa7bdc04e87b3ab696d206a 0000-0003-2804-8164 Anthony Higgins Anthony Higgins true false 2026-05-15 EAAS Reflectometry experiments can benefit substantially from recent advances in machine learning, enabling real-time data analysis, informed decision making during measurements, optimized experimental conditions and ultimately closed-loop experimental workflows. While most prior automation efforts have focused on X-ray reflectometry, neutron reflectometry can also benefit to the same extent. We report the first machine-learning-based pipeline for real-time neutron reflectometry deployed at the Institut Laue–Langevin (ILL), Grenoble, France. The system integrates the reflectorch package into the data acquisition workflow using the IT infrastructure of the facility. This enables analysis that is two orders of magnitude faster than conventional tools, allowing real-time estimation of physical parameters with associated uncertainties and feedback through a graphical user interface. The pipeline has been successfully tested at the ILL, and can be adapted to work at other neutron facilities seeking to enable real-time feedback-driven reflectometry analysis. Journal Article Journal of Applied Crystallography 59 3 International Union of Crystallography (IUCr) 1600-5767 neutron reflectometry; machine learning; online data analysis; experiment automation 1 6 2026 2026-06-01 10.1107/s1600576726002657 COLLEGE NANME Engineering and Applied Sciences School COLLEGE CODE EAAS Swansea University Another institution paid the OA fee We thank the Bundesministerium fu¨r Bildung und Forschung [project VIPR 05D23VT1 (ERUM-DATA)]. We thank the Cluster of Excellence– Machine Learning for Science, funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy (EXC No. 2064/1, project No. 390727645), for support and access to computer resources. We also thank the DFG [grant No. 460248799 to DAPHNE4NFDI, HI1927/7-1 (project 557510229) and SCHR700/50-1]. The authors acknowledge the OSCARS project, which has received funding from the European Commission’s Horizon Europe Research and Innovation programme under grant agreement No. 101129751. Oliver Anyanor thanks the UK Engineering and Physical Sciences Research Council for funding his PhD studentship (grant No. EP/W524694/1). 2026-05-15T11:34:47.8983969 2026-05-15T10:47:56.4027857 Faculty of Science and Engineering School of Engineering and Applied Sciences - Biomedical Engineering Anne Rentzsch 0009-0002-6921-0121 1 Valentin Munteanu 0000-0002-5897-3863 2 Oliver Odira Anyanor 3 Shreya Shah 0009-0001-4330-5918 4 Philipp Gutfreund 0000-0002-7412-8571 5 Rémi Perenon 6 Anthony Higgins 0000-0003-2804-8164 7 Vladimir Starostin 0000-0003-4533-6256 8 Alexander Hinderhofer 0000-0001-8152-6386 9 Dmitry Lapkin 0000-0003-0680-8740 10 Frank Schreiber 0000-0003-3659-6718 11 71909__36742__0daa3fc0e88c496d9b38e8efb1bfa8f6.pdf 71909.VoR.pdf 2026-05-15T11:29:44.8810942 Output 4123086 application/pdf Version of Record true Published under a CC-BY 4.0 licence. true eng https://creativecommons.org/licenses/by/4.0/legalcode
title Towards machine-learning-based on-the-fly analysis of neutron reflectometry
spellingShingle Towards machine-learning-based on-the-fly analysis of neutron reflectometry
Anthony Higgins
title_short Towards machine-learning-based on-the-fly analysis of neutron reflectometry
title_full Towards machine-learning-based on-the-fly analysis of neutron reflectometry
title_fullStr Towards machine-learning-based on-the-fly analysis of neutron reflectometry
title_full_unstemmed Towards machine-learning-based on-the-fly analysis of neutron reflectometry
title_sort Towards machine-learning-based on-the-fly analysis of neutron reflectometry
author_id_str_mv 4db715667aa7bdc04e87b3ab696d206a
author_id_fullname_str_mv 4db715667aa7bdc04e87b3ab696d206a_***_Anthony Higgins
author Anthony Higgins
author2 Anne Rentzsch
Valentin Munteanu
Oliver Odira Anyanor
Shreya Shah
Philipp Gutfreund
Rémi Perenon
Anthony Higgins
Vladimir Starostin
Alexander Hinderhofer
Dmitry Lapkin
Frank Schreiber
format Journal article
container_title Journal of Applied Crystallography
container_volume 59
container_issue 3
publishDate 2026
institution Swansea University
issn 1600-5767
doi_str_mv 10.1107/s1600576726002657
publisher International Union of Crystallography (IUCr)
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Engineering and Applied Sciences - Biomedical Engineering{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Engineering and Applied Sciences - Biomedical Engineering
document_store_str 1
active_str 0
description Reflectometry experiments can benefit substantially from recent advances in machine learning, enabling real-time data analysis, informed decision making during measurements, optimized experimental conditions and ultimately closed-loop experimental workflows. While most prior automation efforts have focused on X-ray reflectometry, neutron reflectometry can also benefit to the same extent. We report the first machine-learning-based pipeline for real-time neutron reflectometry deployed at the Institut Laue–Langevin (ILL), Grenoble, France. The system integrates the reflectorch package into the data acquisition workflow using the IT infrastructure of the facility. This enables analysis that is two orders of magnitude faster than conventional tools, allowing real-time estimation of physical parameters with associated uncertainties and feedback through a graphical user interface. The pipeline has been successfully tested at the ILL, and can be adapted to work at other neutron facilities seeking to enable real-time feedback-driven reflectometry analysis.
published_date 2026-06-01T06:23:14Z
_version_ 1865321277854580736
score 11.105427

Similar Items