In this paper, machine learning techniques are used to reconstruct particle collision pathways. CERN (Conseil européen pour la recherche nucléaire) uses a massive underground particle collider, called the Large Hadron Collider or LHC, to produce particle collisions at extremely high speeds. There are several layers of detectors in the collider that track the pathways of particles as they collide. The data produced from collisions contains an extraneous amount of background noise, i.e., decays from known particle collisions produce fake signal. Particularly, in the first layer of the detector, the pixel tracker, there is an overwhelming amount of background noise that hinders analysts from seeing true track reconstruction. This paper aims to find and optimize methods that are instrumental in figuring out how the true particle track can be decoupled from the background noise produced at the pixel tracker level of the detector. The results of this study include successful implementation of machine learning techniques to classify signal and background from particle collision data. From these results, it was concluded that neural networks are a successful resource for analyzing and processing particle collision data to reconstruct particle pathways.
Fantahun, Kebur; Joseph, Jobin; Purdom, Halle; and Lohia, Nibhrat
"Classification of Pixel Tracks to Improve Track Reconstruction from Proton-Proton Collisions,"
SMU Data Science Review: Vol. 6:
2, Article 8.
Available at: https://scholar.smu.edu/datasciencereview/vol6/iss2/8
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial 4.0 License
Applied Mathematics Commons, Data Science Commons, Elementary Particles and Fields and String Theory Commons, Mathematics Commons, Other Physics Commons, Plasma and Beam Physics Commons, Quantum Physics Commons, Statistics and Probability Commons