E-Thesis 283 views 83 downloads
A study of thermal NRQCD with machine learning methods / SAMUEL OFFLER
Swansea University Author: SAMUEL OFFLER
DOI (Published version): 10.23889/SUthesis.60375
Abstract
The aim of this thesis is to develop a machine learning model capable of the spectral reconstruction of Euclidean lattice correlators at finite temperature. The early part of this thesis is dedicated to a review of the QCD phase diagram and correlation functions to establish the relationship between...
| Published: |
Swansea
2022
|
|---|---|
| Institution: | Swansea University |
| Degree level: | Doctoral |
| Degree name: | Ph.D |
| Supervisor: | Aarts, Gert ; Allton, Chris |
| URI: | https://cronfa.swan.ac.uk/Record/cronfa60375 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
The aim of this thesis is to develop a machine learning model capable of the spectral reconstruction of Euclidean lattice correlators at finite temperature. The early part of this thesis is dedicated to a review of the QCD phase diagram and correlation functions to establish the relationship between the Euclidean correlator and spectral function. An analysis of FASTSUM ensembles of Euclidean correlators is performed to determine effective masses and thermal modification for bottomonium states. An initial model using Kernel Ridge Regression is examined and implemented for the Υ state. The latter part of this thesis focuses on improving the generation of training data for the machine learning method and the machine learning method itself. This work concludes with the implementation of the Kernel Ridge Regression for a variety of bottomonium states. |
|---|---|
| Item Description: |
ORCiD identifier: https://orcid.org/0000-0001-8052-8013 |
| Keywords: |
Lattice QCD, Machine Learning |
| College: |
Faculty of Science and Engineering |