A variational autoencoder for minimally-supervised pulse shape discrimination

Abdullah Abdulaziz, Jianxin Zhou, Ming Fang, Stephen McLaughlin, Angela Di Fulvio, Yoann Altmann

Research output: Contribution to journalArticlepeer-review

7 Downloads (Pure)


We propose a novel approach based on variational autoencoder with Gaussian mixture latent space (GMVAE) to address the challenging problem of pulse shape discrimination (PSD) in organic scintillators, in the presence of pile up. Unlike deterministic charge integration, which is very sensitive to pulse-processing parameters, the GMVAE performances are robust against variations of the hyperparameters. When compared to other supervised machine learning methods, GMVAE requires the fewest training pulses (100) to achieve a classification accuracy within 2% of its optimum performance, i.e., 98.3% accuracy. GMVAE exhibited excellent classification despite the difference in energy spectra between the training and test data sets, which were 14.1 MeV neutron pulses and 239PuBe pulses, respectively. While requiring minimum supervision, GMVAE showed superior PSD performances compared to both deterministic and supervised machine learning approaches. GMVAE is hence particularly suitable for real-time pulse classification, where expert labeling is unavailable and fine tuning of the discrimination parameters impractical.
Original languageEnglish
Article number110496
JournalAnnals of Nuclear Energy
Early online date15 Apr 2024
Publication statusE-pub ahead of print - 15 Apr 2024


  • Organic scintillators
  • Pulse shape discrimination
  • Semi-supervised classification
  • Variational autoencoder

ASJC Scopus subject areas

  • Nuclear Energy and Engineering


Dive into the research topics of 'A variational autoencoder for minimally-supervised pulse shape discrimination'. Together they form a unique fingerprint.

Cite this