Low Activity Tritium Detection in CCDs Using Deep Learning Techniques

TL;DR

This paper investigates the use of deep learning techniques, especially CNNs and autoencoders, to improve the detection of low-energy tritium decay signals in CCDs, enhancing sensitivity and background rejection for environmental and nuclear safety applications.

Contribution

It introduces a novel application of deep learning methods, including CNNs and autoencoders, for tritium detection in CCDs, demonstrating improved classification performance over classical techniques.

Findings

CNN outperforms classical methods in signal classification

Autoencoder shows potential for background-agnostic detection

Deep learning enhances sensitivity and background rejection

Abstract

This study explores the use of charge-coupled devices (CCDs) for detecting low-energy beta particles from tritium decay - a critical signal for nuclear safety, nuclear nonproliferation, and environmental monitoring. We employ a dual approach utilizing both measured CCD data and detailed Geant4 simulations. Our analysis compares classical techniques with advanced deep learning methods, including convolutional neural networks (CNNs), autoencoders trained exclusively on tritium data, and preliminary studies on boosted decision trees (BDTs). The CNN, trained on mixed signal/background datasets, demonstrates superior classification performance, while the autoencoder shows the potential of unsupervised, background-agnostic strategies when background characteristics are poorly defined. These results highlight the excellent sensitivity achievable thanks to the background rejection made possible by information-rich CCD data, paving the way for improved portable tritium monitoring.