Cyclotron Radiation Emission Spectroscopy Signal Classification with Machine Learning in Project 8
A. Ashtari Esfahani, S. Boser, N. Buzinsky, R. Cervantes, C. Claessens, L. de Viveiros, M. Fertl, J. A. Formaggio, L. Gladstone, M. Guigue, K. M. Heeger, J. Joh… 展开作者
A. Ashtari Esfahani, S. Boser, N. Buzinsky, R. Cervantes, C. Claessens, L. de Viveiros, M. Fertl, J. A. Formaggio, L. Gladstone, M. Guigue, K. M. Heeger, J. Johnston, A. M. Jones, K. Kazkaz, B. H. LaRoque, A. Lindman, E. Machado, B. Monreal, E. C. Morrison, J. A. Nikkel, E. Novitski, N. S. Oblath, W. Pettus, R. G. H. Robertson, G. Rybka, L. Saldana, V. Sibille, M. Schram, P. L. Slocum, Y. H. Sun, T. Thummler, B. A. VanDevender, T. E. Weiss, T. Wendler, E. Zayas
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.
