Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

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

Journal Article · · New Journal of Physics
 [1];  [2];  [3];  [1];  [2];  [4];  [5]; ORCiD logo [3];  [6];  [7];  [8];  [3];  [9];  [10];  [9];  [2];  [1];  [6];  [9];  [8] more »; ORCiD logo [1];  [9];  [1];  [1]; ORCiD logo [1];  [8];  [3];  [9]; ORCiD logo [8];  [6];  [11];  [9];  [3];  [4];  [3] « less
  1. Univ. of Washington, Seattle, WA (United States). Dept. of Physics
  2. Univ. of Mainz (Germany)
  3. Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
  4. Pennsylvania State Univ., University Park, PA (United States)
  5. Univ. of Washington, Seattle, WA (United States). Dept. of Physics; Univ. of Mainz (Germany)
  6. Case Western Reserve Univ., Cleveland, OH (United States)
  7. Pacific Northwest National Lab. (PNNL), Richland, WA (United States); Sorbonne Univ., Paris (France)
  8. Yale Univ., New Haven, CT (United States)
  9. Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
  10. Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
  11. Karlsruhe Inst. of Technology (KIT) (Germany)
+ Show Author Affiliations

The Cyclotron Radiation Emission Spectroscopy (CRES) technique pioneered by Project 8 measures cyclotron radiation from individual electrons 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. Here, we develop machine learning models to classify CRES signals with high accuracy based on these traits, improve the resultant frequency spectrum, and offer the potential for a sophisticated analysis which will help Project 8 achieve tritium endpoint measurement in the future.

Research Organization:
Pacific Northwest National Laboratory (PNNL), Richland, WA (United States); Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Nuclear Physics (NP); National Science Foundation (NSF); German Research Foundation (DFG)
Grant/Contract Number:
AC05-76RL01830; SC0011091; SC0019088; FG02-97ER41020; SC0012654; AC52-07NA27344
OSTI ID:
1616702
Report Number(s):
PNNL-SA--146046
Journal Information:
New Journal of Physics, Journal Name: New Journal of Physics Journal Issue: 3 Vol. 22; ISSN 1367-2630
Publisher:
IOP PublishingCopyright Statement
Country of Publication:
United States
Language:
English

References (10)

Support-vector networks journal September 1995
Precision measurement of the conversion electron spectrum of83m Kr with a solenoid retarding spectrometer journal March 1992
ROOT — An object oriented data analysis framework journal April 1997
Determining the neutrino mass with cyclotron radiation emission spectroscopy—Project 8 journal March 2017
Electron radiated power in cyclotron radiation emission spectroscopy experiments journal May 2019
Single-Electron Detection and Spectroscopy via Relativistic Cyclotron Radiation journal April 2015
Correspondence of electron spectra from photoionization and nuclear internal conversion journal October 1991
LIBSVM: A library for support vector machines journal April 2011
Use of the Hough transformation to detect lines and curves in pictures journal January 1972
Stan : A Probabilistic Programming Language journal January 2017

Similar Records

Related Subjects

73 NUCLEAR PHYSICS AND RADIATION PHYSICS
cyclotron radiation
machine learning
neutrino mass
support vector machine