SINAPSE: A lightweight deep learning framework for accurate and explainable neutron-γ discrimination
Abstract
Traditionally, neutron-γ discrimination in organic scintillators relies on techniques such as time-of-flight (ToF) selection and pulse-shape discrimination (PSD). However, particle identification through graphical cuts remains challenging in the low-charge regime due to poor signal-to-noise ratios (SNR). In this work, we propose SINAPSE, a lightweight deep learning framework for accurate and explainable neutron-γ discrimination in the low-charge regime. The framework employs a dual-branch architecture that combines a 1-dimensional convolutional autoencoder for waveform denoising with a classifier for particle identification. Random augmentations are applied to high-SNR waveforms to simulate low-charge conditions, enabling robust extrapolation into regimes where conventional PSD labels are unreliable. We show that SINAPSE achieves superior denoising performance compared to conventional digital signal processing techniques, and outputs well-calibrated probabilities, consistent with traditional graphical cuts. Finally, we apply SHAP (SHapley Additive exPlanations) values to show that model decisions are driven by physically meaningful pulse-shape features, confirming consistency with established PSD principles.
Related
- An Explainable Machine Learning Framework for Predicting Blood-Brain Barrier Permeability Using Molecular Descriptors
- Efficient SPAD reconstruction framework with time-frequency domain compression and lightweight joint depth-intensity optimization
- A Fast and Accurate Source-Mask Optimization Flow Using a Unified Abbe-Hopkins Framework
- Lifting: Quantum State Discrimination Framework for Mid-Circuit Measurements
- BSMScanner: a lightweight framework for beyond-the-Standard-Model global fits
BibTeX
@misc{carreau2026sinapse,
title = {{SINAPSE: A lightweight deep learning framework for accurate and explainable neutron-$γ$ discrimination}},
author = {Thomas Carreau and Adrien Matta and Owen Syrett and Benoît Mauss and David Etasse and Cyril Lenain and Pierre Morfouace and Julien Taieb and David Regnier and Patrick Copp and Matthew Devlin and Charlène Surault and Jason Surbrook},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.13627},
eprint = {2605.13627},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.13627},
}
RIS
TY - UNPB
TI - SINAPSE: A lightweight deep learning framework for accurate and explainable neutron-γ discrimination
AU - Thomas Carreau
AU - Adrien Matta
AU - Owen Syrett
AU - Benoît Mauss
AU - David Etasse
AU - Cyril Lenain
AU - Pierre Morfouace
AU - Julien Taieb
AU - David Regnier
AU - Patrick Copp
AU - Matthew Devlin
AU - Charlène Surault
AU - Jason Surbrook
PY - 2026
DA - 2026/09/04
PB - arXiv
DO - 10.48550/arxiv.2605.13627
UR - https://arxiv.org/abs/2605.13627
AB - Traditionally, neutron-γ discrimination in organic scintillators relies on techniques such as time-of-flight (ToF) selection and pulse-shape discrimination (PSD). However, particle identification through graphical cuts remains challenging in the low-charge regime due to poor signal-to-noise ratios (SNR). In this work, we propose SINAPSE, a lightweight deep learning framework for accurate and explainable neutron-γ discrimination in the low-charge regime. The framework employs a dual-branch architecture that combines a 1-dimensional convolutional autoencoder for waveform denoising with a classifier for particle identification. Random augmentations are applied to high-SNR waveforms to simulate low-charge conditions, enabling robust extrapolation into regimes where conventional PSD labels are unreliable. We show that SINAPSE achieves superior denoising performance compared to conventional digital signal processing techniques, and outputs well-calibrated probabilities, consistent with traditional graphical cuts. Finally, we apply SHAP (SHapley Additive exPlanations) values to show that model decisions are driven by physically meaningful pulse-shape features, confirming consistency with established PSD principles.
ER -