학술논문
Cyclotron Radiation Emission Spectroscopy Signal Classification with Machine Learning in Project 8
Document Type
Working Paper
Author
Esfahani, A. Ashtari; Boser, S.; Buzinsky, N.; Cervantes, R.; Claessens, C.; de Viveiros, L.; Fertl, M.; Formaggio, J. A.; Gladstone, L.; Guigue, M.; Heeger, K. M.; Johnston, J.; Jones, A. M.; Kazkaz, K.; LaRoque, B. H.; Lindman, A.; Machado, E.; Monreal, B.; Morrison, E. C.; Nikkel, J. A.; Novitski, E.; Oblath, N. S.; Pettus, W.; Robertson, R. G. H.; Rybka, G.; Saldana, L.; Sibille, V.; Schram, M.; Slocum, P. L.; Sun, Y. H.; Thummler, T.; VanDevender, B. A.; Weiss, T. E.; Wendler, T.; Zayas, E.
Source
New Journal of Physics, Volume 22, March 2020
Subject
Language
Abstract
The Cyclotron Radiation Emission Spectroscopy (CRES) technique pioneered by Project 8 measures electromagnetic radiation from individual electrons gyrating in a background magnetic field to construct a highly precise energy spectrum for beta decay studies and other applications. The detector, magnetic trap geometry, and electron dynamics give rise to a multitude of complex electron signal structures which carry information about distinguishing physical traits. With machine learning models, we develop a scheme based on these traits to analyze and classify CRES signals. Understanding and proper use of these traits will be instrumental to improve cyclotron frequency reconstruction and help Project 8 achieve world-leading sensitivity on the tritium endpoint measurement in the future.
Comment: 30 pages, 16 figures
Comment: 30 pages, 16 figures