Cyclotron Radiation Emission Spectroscopy Signal Classification with Machine Learning in Project 8
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.
Keywords
Cite
@article{arxiv.1909.08115,
title = {Cyclotron Radiation Emission Spectroscopy Signal Classification with Machine Learning in Project 8},
author = {A. Ashtari Esfahani and S. Boser and N. Buzinsky and R. Cervantes and C. Claessens and L. de Viveiros and M. Fertl and J. A. Formaggio and L. Gladstone and M. Guigue and K. M. Heeger and J. Johnston and A. M. Jones and K. Kazkaz and B. H. LaRoque and A. Lindman and E. Machado and B. Monreal and E. C. Morrison and J. A. Nikkel and E. Novitski and N. S. Oblath and W. Pettus and R. G. H. Robertson and G. Rybka and L. Saldana and V. Sibille and M. Schram and P. L. Slocum and Y. H. Sun and T. Thummler and B. A. VanDevender and T. E. Weiss and T. Wendler and E. Zayas},
journal= {arXiv preprint arXiv:1909.08115},
year = {2020}
}
Comments
30 pages, 16 figures