Deep Neural Networks for Energy and Position Reconstruction in EXO-200

Abstract

We apply deep neural networks (DNN) to data from the EXO-200 experiment. In the studied cases, the DNN is able to reconstruct the relevant parameters - total energy and position - directly from raw digitized waveforms, with minimal exceptions. For the first time, the developed algorithms are evaluated on real detector calibration data. The accuracy of reconstruction either reaches or exceeds what was achieved by the conventional approaches developed by EXO-200 over the course of the experiment. Most existing DNN approaches to event reconstruction and classification in particle physics are trained on Monte Carlo simulated events. Such algorithms are inherently limited by the accuracy of the simulation. We describe a unique approach that, in an experiment such as EXO-200, allows to successfully perform certain reconstruction and analysis tasks by training the network on waveforms from experimental data, either reducing or eliminating the reliance on the Monte Carlo.

arXiv commentAccepted version. 33 pages, 28 figures

References in corpus (12)

• Searching for Exotic Particles in High-Energy Physics with Deep Learning
• Search for Neutrinoless Double-Beta Decay in ${}^{136}$Xe with EXO-200
• A Convolutional Neural Network Neutrino Event Classifier
• Search for Neutrinoless Double-Beta Decay with the Upgraded EXO-200 Detector
• Jet Flavor Classification in High-Energy Physics with Deep Neural Networks
• An improved measurement of the 2νββ half-life of Xe-136 with EXO-200
• The EXO-200 detector, part I: Detector design and construction
• Correlated Fluctuations between Luminescence and Ionization in Liquid Xenon
• Convolutional Neural Networks Applied to Neutrino Events in a Liquid Argon Time Projection Chamber
• Background rejection in NEXT using deep neural networks
• Measurement of the Drift Velocity and Transverse Diffusion of Electrons in Liquid Xenon with the EXO-200 Detector
• An Optimal Energy Estimator to Reduce Correlated Noise for the EXO-200 Light Readout

Cited by in corpus (25)

• Toward the discovery of matter creation with neutrinoless double-beta decay
• Search for Neutrinoless Double-Beta Decay with the Complete EXO-200 Dataset
• A Review of Basic Energy Reconstruction Techniques in Liquid Xenon and Argon Detectors for Dark Matter and Neutrino Physics Using NEST
• Lorentz Boost Networks: Autonomous Physics-Inspired Feature Engineering
• Semantic Segmentation with a Sparse Convolutional Neural Network for Event Reconstruction in MicroBooNE
• Deep learning based pulse shape discrimination for germanium detectors
• Improved Energy Reconstruction in NOvA with Regression Convolutional Neural Networks
• Machine Learning Methods for Track Classification in the AT-TPC
• SARM: Sparse Autoregressive Model for Scalable Generation of Sparse Images in Particle Physics
• A Review on Machine Learning for Neutrino Experiments
• A Review of NEST Models for Liquid Xenon and Exhaustive Comparison to Other Approaches
• Identification of Patterns in Cosmic-Ray Arrival Directions using Dynamic Graph Convolutional Neural Networks
• Simulation of charge readout with segmented tiles in nEXO
• Optimizing Observables with Machine Learning for Better Unfolding
• Towards an automated data cleaning with deep learning in CRESST
• Learning Uncertainties the Frequentist Way: Calibration and Correlation in High Energy Physics
• Machine learning method for ${}^{12}$C event classification and reconstruction in the active target time-projection chamber
• Bias and Priors in Machine Learning Calibrations for High Energy Physics
• Fast and Flexible Analysis of Direct Dark Matter Search Data with Machine Learning
• A machine learning-based methodology for pulse classification in dual-phase xenon time projection chambers
• Search for Two-neutrino Double-Beta Decay of ${}^{136}\mathrm{Xe}$ to the $0_1^{+}$ excited state of ${}^{136}\mathrm{Ba}$ with the Complete EXO-200 Dataset
• Domain-informed neural networks for interaction localization within astroparticle experiments
• Deep learning based track reconstruction on CEPC luminometer
• Suppression of accidental backgrounds with deep neural networks in the PandaX-II experiment
• Search for Double Beta Decays of ${}^{134}$Xe with EXO-200 Phase II