Exploiting the Latent Space of Deep AutoEncoders for the Identification of Signal Pulses in Noisy Time-Series
Open Access
Abstract
We propose a data-driven procedure, based on convolutional variational autoencoders, to identify the presence of signal pulses in long time series. The dataset consists of synthetic waveforms, each composed of non-Gaussian noise and a log-normal-shaped signal of variable intensity, with a length of 10,000 samples. The model heavily compresses the input waveforms, allowing a direct study of such a reduced representation. After training for 150 epochs on 7500 waveforms, a region in the latent space where the network encodes time-series presenting only background noise emerges, allowing, in turn, to tag as candidates for containing a signal those falling outside. When applied to a test dataset of freshly generated waveforms, 100% of events with signal amplitudes well above the baseline noise are correctly labelled, and this fraction only decreases for amplitudes comparable with accidental noise pulses. This approach was designed to fully exploit the measurements in dual-phase Liquid Argon Time Projection Chambers, as the one of the Recoil Directionality experiment, built in the context of the Darkside project.Keywords
All Related Versions
Funding Information
- Fondazione ICSC Centro Nazionale di Ricerca in High Performance Computing, Big Data e Quantum Computing (-)
This publication has 43 references indexed in Scilit:
- Applications of machine learning in gravitational-wave research with current interferometric detectorsLiving Reviews in Relativity, 2025
- DarkSide-20k sensitivity to light dark matter particlesCommunications Physics, 2024
- Deep generative models for detector signature simulation: A taxonomic reviewReviews in Physics, 2024
- Deep Learning2024
- Extracting low energy signals from raw LArTPC waveforms using deep learning techniques — A proof of conceptNuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2022
- Variational autoencoders for new physics mining at the Large Hadron ColliderJournal of High Energy Physics, 2019
- Big Bang synthesis of nuclear dark matterJournal of High Energy Physics, 2015
- First results from the DarkSide-50 dark matter experiment at Laboratori Nazionali del Gran SassoPhysics Letters B, 2015
- Dark matter production in the early Universe: Beyond the thermal WIMP paradigmPhysics Reports, 2015
- Particle dark matter: evidence, candidates and constraintsPhysics Reports, 2005