Xenon signal denoising via supervised, semi-supervised, and unsupervised models
Open Access
- 26 July 2026
- journal article
- Published by Springer Nature in The European Physical Journal C
- Vol. 86 (7) , 875
Abstract
This study presents a denoising algorithm trained using machine learning to improve the energy resolution of a single-phase liquid xenon time projection chamber for neutrinoless double beta decay detection. Supervised, unsupervised, and semi-supervised models are demonstrated to significantly remove noise from simulated measurements while preserving signal information. The supervised model achieves an energy resolution of $$<1\%$$ , while the semi-supervised models achieve energy resolutions of $$\sim 1\%$$ , and the unsupervised model performance is $$\sim 1.5\%$$ . This work is evidence that machine learning denoising can improve energy resolution compared to traditional algorithms, even when experimentalists lack perfect a priori knowledge of the signals. Such models provide a realistic path toward next-generation sensitivity in $$0\nu \beta \beta $$ searches.
Keywords
Funding Information
- Lawrence Livermore National Laboratory (LLNL LDRD 24-ERD-002)
This publication has 27 references indexed in Scilit:
- On the discriminability of self-supervised representation learningInformation Sciences, 2025
- Neural network reconstruction of non-Gaussian initial conditions from dark matter halosJournal of Cosmology and Astroparticle Physics, 2025
- Robust multi‐coil MRI reconstruction via self‐supervised denoisingMagnetic Resonance in Medicine, 2025
- Investigating self-supervised image denoising with denaturationNeural Networks, 2024
- nEXO: neutrinoless double beta decay search beyond 10 28 year half-life sensitivityJournal of Physics G: Nuclear and Particle Physics, 2021
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Cold electronics for "Giant" Liquid Argon Time Projection ChambersJournal of Physics: Conference Series, 2011
- Geant4—a simulation toolkitNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2003
- Barygenesis without grand unificationPhysics Letters B, 1986
- Smoothing and Differentiation of Data by Simplified Least Squares Procedures.Analytical Chemistry, 1964