kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Identifying the Higgs Boson with Machine Learning Methods
KTH, School of Engineering Sciences (SCI), Physics.
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Identifiering av Higgsbosonen med maskininlärningsmetoder (Swedish)
Abstract [en]

This report introduces a signal discrimination framework for particle physics processes, including a novel ensemble learning method using multiple machine learning models. The framework is tested with a signal region of the Higgs boson decay channel H → WW∗ → lνlν with two or more jets. The final state consists of leptons with the same flavor but opposite electrical charges, and the Higgs bosons are produced by Vector-boson fusion (VBF). The background region consists of the three largest processes with the same final state without originating from the signal process. Multiple models are trained and evaluated on Monte Carlo samples corresponding to a subset of the full Run 2 dataset of proton-proton collisions recorded by the ATLAS experiment at CERN’s Large Hadron Collider (LHC). The analysis in this report shows that ensemble methods improve background rejection leading to increased discrimination between the signal and background region compared with individual machine learning models.

Abstract [sv]

Denna rapport introducerar ett ramverk för signalseparering för processer inom partikelfysik, inklusive en ny ensemblemetod. Ensemblemetoden använder sig av flera maskininlärningsmodeller. Ramverket testas med en signalregion bestående av en sönderfallskanal för Higgsbosonen H → WW∗ → lvlv med två eller flera jets. Leptonerna i sluttillståndet är av samma typ men motsatt laddning. Higgsbosonerna produceras genom så kallad "Vector-boson fusion (VBF)". Bakgrundsregionen innehåller de tre största processerna som har samma sluttillstånd utan att komma ifrån signalprocessen. Flertal modeller tränas och utvärderas på Monte Carlo-simuleringar som motsvarar en delmängd av hela Run 2-datasetet bestående av proton-proton kollisioner som samlats in av ATLAS-experimentet vid CERNs Large Hadron Collider (LHC). Rapporten visar att ensemblemetoden förbättrar bakgrundsidentifieringen vilket leder till förbättrad separation mellan signal- och bakgrundsregionen jämfört med individuella maskininlärningsmodeller.

Place, publisher, year, edition, pages
2024.
Series
TRITA-SCI-GRU ; 2024:111
Keywords [en]
particle physics, Higgs boson, machine learning
Keywords [sv]
partikelfysik, Higgsbosonen, maskininlärning
National Category
Physical Sciences
Identifiers
URN: urn:nbn:se:kth:diva-347953OAI: oai:DiVA.org:kth-347953DiVA, id: diva2:1872323
External cooperation
ATLAS at CERN
Subject / course
Physics
Educational program
Master of Science - Engineering Physics
Supervisors
Examiners
Available from: 2024-06-18 Created: 2024-06-18 Last updated: 2024-06-24Bibliographically approved

Open Access in DiVA

fulltext(43199 kB)565 downloads
File information
File name FULLTEXT02.pdfFile size 43199 kBChecksum SHA-512
6d92ead3c5d56940a10cd6bedcfddc0c730b96808b0e772c34ca978ba5f29b17453060de4985bf5ea329517791b92bb64b6ab126c91d38f514fb0243c1e76659
Type fulltextMimetype application/pdf

By organisation
Physics
Physical Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 580 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 375 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf