No Cover Image

E-Thesis 342 views 109 downloads

Machine learning methods for Antihydrogen Detection / LUKAS GOLINO

Swansea University Author: LUKAS GOLINO

DOI (Published version): 10.23889/SUThesis.69339

Abstract

Antihydrogen, composing an antiproton and positron, is the only bound state of two antiparticles yet to be synthesised, making for an enticing system to study the purported symmetry of matter and antimatter. As antihydrogen does not occur naturally in the observable universe, any study of this atom...

Full description

Published: Swansea University, Wales, UK 2025
Institution: Swansea University
Degree level: Doctoral
Degree name: Ph.D
Supervisor: Madsen, N., and Aarts, G.
URI: https://cronfa.swan.ac.uk/Record/cronfa69339
first_indexed 2025-04-24T10:07:27Z
last_indexed 2025-04-25T05:20:57Z
id cronfa69339
recordtype RisThesis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2025-04-24T11:14:03.7184443</datestamp><bib-version>v2</bib-version><id>69339</id><entry>2025-04-24</entry><title>Machine learning methods for Antihydrogen Detection</title><swanseaauthors><author><sid>92ac4d0f947856adcfde3d39701645a1</sid><firstname>LUKAS</firstname><surname>GOLINO</surname><name>LUKAS GOLINO</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-04-24</date><abstract>Antihydrogen, composing an antiproton and positron, is the only bound state of two antiparticles yet to be synthesised, making for an enticing system to study the purported symmetry of matter and antimatter. As antihydrogen does not occur naturally in the observable universe, any study of this atom requires it to be synthesised in a lab, which the ALPHA experiment is routinely able to do. However, the absolute numbers are small and e&#xFB03;cient detection is crucial for the experiment. To detect these atoms, ALPHA deploys two main annihilation detectors: asilicon vertex detector and a new time projection chamber installed in 2018. A key challenge for both detectors is distinguishing between antimatter annihilations and background events (e.g. cosmic radiation), a task for which machine learning is well suited. Presently, for the silicon vertex detector, this is done with high-level variables, while the time projection chamber has no way of &#xFB01;ltering these events. In the present work, we have developed the &#xFB01;rst models capable of &#xFB01;ltering events in the time projection chamber, which proved vital in the &#xFB01;rst measurement of the e&#xFB00;ect of gravity on the motion of antimatter. A &#xFB01;rst-of-its-kind deep learning model trained on low-level data from the silicon vertex detector has been developed, and it can successfully classify events to a high degree of accuracy. Further, the newest models trained for the silicon vertex detector are presented. The use of these models on real data is included, and all results generated by ALPHA from the 2022-2024 experimental runs will use the models described in this thesis. Finally, the transverse beam pro&#xFB01;le in the accelerators throughout CERN (such as the one used to provide antiprotons to ALPHA) is an important metric for successful operation. The signi&#xFB01;cant increase in beam intensities poses a challenge that make the currently deployed correcting magnetic &#xFB01;elds undesirable. The possibility of using machine learning to reconstruct beam pro&#xFB01;les in the Proton Synchrotron is presented, and a &#xFB01;rst attempt at applying these models to real data is included which, despite a troubled dataset, shows promising results.</abstract><type>E-Thesis</type><journal/><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication>Swansea University, Wales, UK</placeOfPublication><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Antimatter, detection, machine learning, simulations</keywords><publishedDay>27</publishedDay><publishedMonth>2</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-02-27</publishedDate><doi>10.23889/SUThesis.69339</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><supervisor>Madsen, N., and Aarts, G.</supervisor><degreelevel>Doctoral</degreelevel><degreename>Ph.D</degreename><degreesponsorsfunders>EPSRC doctoral training grant</degreesponsorsfunders><apcterm/><funders>EPSRC doctoral training grant</funders><projectreference/><lastEdited>2025-04-24T11:14:03.7184443</lastEdited><Created>2025-04-24T11:02:54.8497289</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Biosciences, Geography and Physics - Physics</level></path><authors><author><firstname>LUKAS</firstname><surname>GOLINO</surname><order>1</order></author></authors><documents><document><filename>69339__34082__d7f02febe2fe4e2cac466a3bb1a8f7d1.pdf</filename><originalFilename>2024_Golino_L.final.69339.pdf</originalFilename><uploaded>2025-04-24T11:09:22.8113004</uploaded><type>Output</type><contentLength>100850445</contentLength><contentType>application/pdf</contentType><version>E-Thesis &#x2013; open access</version><cronfaStatus>true</cronfaStatus><documentNotes>Copyright: The Author, Lukas M. Golino, 2024</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents><OutputDurs/></rfc1807>
spelling 2025-04-24T11:14:03.7184443 v2 69339 2025-04-24 Machine learning methods for Antihydrogen Detection 92ac4d0f947856adcfde3d39701645a1 LUKAS GOLINO LUKAS GOLINO true false 2025-04-24 Antihydrogen, composing an antiproton and positron, is the only bound state of two antiparticles yet to be synthesised, making for an enticing system to study the purported symmetry of matter and antimatter. As antihydrogen does not occur naturally in the observable universe, any study of this atom requires it to be synthesised in a lab, which the ALPHA experiment is routinely able to do. However, the absolute numbers are small and efficient detection is crucial for the experiment. To detect these atoms, ALPHA deploys two main annihilation detectors: asilicon vertex detector and a new time projection chamber installed in 2018. A key challenge for both detectors is distinguishing between antimatter annihilations and background events (e.g. cosmic radiation), a task for which machine learning is well suited. Presently, for the silicon vertex detector, this is done with high-level variables, while the time projection chamber has no way of filtering these events. In the present work, we have developed the first models capable of filtering events in the time projection chamber, which proved vital in the first measurement of the effect of gravity on the motion of antimatter. A first-of-its-kind deep learning model trained on low-level data from the silicon vertex detector has been developed, and it can successfully classify events to a high degree of accuracy. Further, the newest models trained for the silicon vertex detector are presented. The use of these models on real data is included, and all results generated by ALPHA from the 2022-2024 experimental runs will use the models described in this thesis. Finally, the transverse beam profile in the accelerators throughout CERN (such as the one used to provide antiprotons to ALPHA) is an important metric for successful operation. The significant increase in beam intensities poses a challenge that make the currently deployed correcting magnetic fields undesirable. The possibility of using machine learning to reconstruct beam profiles in the Proton Synchrotron is presented, and a first attempt at applying these models to real data is included which, despite a troubled dataset, shows promising results. E-Thesis Swansea University, Wales, UK Antimatter, detection, machine learning, simulations 27 2 2025 2025-02-27 10.23889/SUThesis.69339 COLLEGE NANME COLLEGE CODE Swansea University Madsen, N., and Aarts, G. Doctoral Ph.D EPSRC doctoral training grant EPSRC doctoral training grant 2025-04-24T11:14:03.7184443 2025-04-24T11:02:54.8497289 Faculty of Science and Engineering School of Biosciences, Geography and Physics - Physics LUKAS GOLINO 1 69339__34082__d7f02febe2fe4e2cac466a3bb1a8f7d1.pdf 2024_Golino_L.final.69339.pdf 2025-04-24T11:09:22.8113004 Output 100850445 application/pdf E-Thesis – open access true Copyright: The Author, Lukas M. Golino, 2024 true eng
title Machine learning methods for Antihydrogen Detection
spellingShingle Machine learning methods for Antihydrogen Detection
LUKAS GOLINO
title_short Machine learning methods for Antihydrogen Detection
title_full Machine learning methods for Antihydrogen Detection
title_fullStr Machine learning methods for Antihydrogen Detection
title_full_unstemmed Machine learning methods for Antihydrogen Detection
title_sort Machine learning methods for Antihydrogen Detection
author_id_str_mv 92ac4d0f947856adcfde3d39701645a1
author_id_fullname_str_mv 92ac4d0f947856adcfde3d39701645a1_***_LUKAS GOLINO
author LUKAS GOLINO
author2 LUKAS GOLINO
format E-Thesis
publishDate 2025
institution Swansea University
doi_str_mv 10.23889/SUThesis.69339
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 Biosciences, Geography and Physics - Physics{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Biosciences, Geography and Physics - Physics
document_store_str 1
active_str 0
description Antihydrogen, composing an antiproton and positron, is the only bound state of two antiparticles yet to be synthesised, making for an enticing system to study the purported symmetry of matter and antimatter. As antihydrogen does not occur naturally in the observable universe, any study of this atom requires it to be synthesised in a lab, which the ALPHA experiment is routinely able to do. However, the absolute numbers are small and efficient detection is crucial for the experiment. To detect these atoms, ALPHA deploys two main annihilation detectors: asilicon vertex detector and a new time projection chamber installed in 2018. A key challenge for both detectors is distinguishing between antimatter annihilations and background events (e.g. cosmic radiation), a task for which machine learning is well suited. Presently, for the silicon vertex detector, this is done with high-level variables, while the time projection chamber has no way of filtering these events. In the present work, we have developed the first models capable of filtering events in the time projection chamber, which proved vital in the first measurement of the effect of gravity on the motion of antimatter. A first-of-its-kind deep learning model trained on low-level data from the silicon vertex detector has been developed, and it can successfully classify events to a high degree of accuracy. Further, the newest models trained for the silicon vertex detector are presented. The use of these models on real data is included, and all results generated by ALPHA from the 2022-2024 experimental runs will use the models described in this thesis. Finally, the transverse beam profile in the accelerators throughout CERN (such as the one used to provide antiprotons to ALPHA) is an important metric for successful operation. The significant increase in beam intensities poses a challenge that make the currently deployed correcting magnetic fields undesirable. The possibility of using machine learning to reconstruct beam profiles in the Proton Synchrotron is presented, and a first attempt at applying these models to real data is included which, despite a troubled dataset, shows promising results.
published_date 2025-02-27T05:24:23Z
_version_ 1851550611808452608
score 11.090091

Similar Items