Cyclotron radiation emission spectroscopy signal classification with machine learning in project 8

The cyclotron radiation emission spectroscopy (CRES) technique pioneered by Project 8measures electromagnetic radiation fromindividual electrons gyrating in a backgroundmagnetic field to construct a highly precise energy spectrumfor beta decay studies and other applications. The detector,magnetic trap geometry and electron dynamics give rise to amultitude of complex electron signal structures which carry information about distinguishing physical traits.Withmachine learningmodels, we develop a scheme based on these traits to analyze and classifyCRES signals. Proper understanding and use of these traits will be instrumental to improve cyclotron frequency reconstruction and boost the potential of Project 8 to achieveworld-leading sensitivity on the tritiumendpointmeasurement in the future.