Fedotovs, Filips;
(2025)
Optimisation of the SHiP muon shield and event reconstruction in the SND@LHC emulsions using machine learning.
Doctoral thesis (Ph.D), UCL (University College London).
Preview |
Text
Fedotovs_10215623_Thesis.pdf Download (28MB) | Preview |
Abstract
This work studies the use of machine learning techniques in high-energy physics to increase the discovery potential of two experiments. Five different studies were carried out within two CERN experiments: SHiP and SND@LHC, the former being an approved proposal, and the latter having taken data since the start of LHC Run 3. These experiments, run by a largely overlapping collaboration, are designed to measure or discover Feebly Interacting Particles (FIPs), predicted by Hidden Val ley theories, or neutrinos. They require very strong signal/background separation, making them ideal testing grounds for Machine Learning techniques. One of the key issues of the SHiP proposal is the muon shield, which is expected to deflect muons produced by the interactions of the SPS beam on a beam dump. In order for the experiment to reach its sensitivity to FIPs, no muon can reach the sensitive part of the detector, leading to a very complex magnetic field structure. Evolutionary algorithms were employed to derive an optimal magnetic shield design, also accounting for practical factors. The SND@LHC detector, located 480 metres away from the ATLAS collision point, behind a large amount of concrete and rock, measures neutrinos and searches for FIPs interacting in an emulsion tracker. Neural networks were applied to analyse high-resolution emulsion data in the presence of noise and misalignments. Multiple aspects of the reconstruction and analysis have been covered, including tracking, vertexing, particle classification, and momentum estimation. Under specific conditions, machine learning can greatly improve the performance of standard algorithms, even if their practical implementation is far from straightforward...
| Type: | Thesis (Doctoral) |
|---|---|
| Qualification: | Ph.D |
| Title: | Optimisation of the SHiP muon shield and event reconstruction in the SND@LHC emulsions using machine learning |
| Open access status: | An open access version is available from UCL Discovery |
| Language: | English |
| Additional information: | Copyright © The Author 2025. Original content in this thesis is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) Licence (https://creativecommons.org/licenses/by-nc/4.0/). Any third-party copyright material present remains the property of its respective owner(s) and is licensed under its existing terms. Access may initially be restricted at the author’s request. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Maths and Physical Sciences > Dept of Physics and Astronomy |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10215623 |
Archive Staff Only
 |
View Item |
