Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers

Abstract

For current and future neutrino oscillation experiments using large Liquid Argon Time Projection Chambers (LAr-TPCs), a key challenge is identifying neutrino interactions from the pervading cosmic-ray background. Rejection of such background is often possible using traditional cut-based selections, but this typically requires the prior use of computationally expensive reconstruction algorithms. This work demonstrates an alternative approach of using a 3D Submanifold Sparse Convolutional Network trained on low-level information from the scintillation light signal of interactions inside LAr-TPCs. This technique is applied to example simulations from ICARUS, the far detector of the Short Baseline Neutrino (SBN) program at Fermilab. The results of the network, show that cosmic background is reduced by up to 76.3% whilst neutrino interaction selection efficiency remains over 98.9%. We further present a way to mitigate potential biases from imperfect input simulations by applying Domain Adversarial Neural Networks (DANNs), for which modified simulated samples are introduced to imitate real data and a small portion of them are used for adverserial training. A series of mock-data studies are performed and demonstrate the effectiveness of using DANNs to mitigate biases, showing neutrino interaction selection efficiency performances significantly better than that achieved without the adversarial training.

arXiv comment9 pages, 6 figures

References in corpus (14)

• TensorFlow: A system for large-scale machine learning
• Graph Neural Networks: A Review of Methods and Applications
• The GENIE Neutrino Monte Carlo Generator
• Submanifold Sparse Convolutional Networks
• The Neutrino Flux prediction at MiniBooNE
• A Proposal for a Three Detector Short-Baseline Neutrino Oscillation Program in the Fermilab Booster Neutrino Beam
• A Convolutional Neural Network Neutrino Event Classifier
• A Deep Neural Network for Pixel-Level Electromagnetic Particle Identification in the MicroBooNE Liquid Argon Time Projection Chamber
• First Observation of Low Energy Electron Neutrinos in a Liquid Argon Time Projection Chamber
• Neutrino interaction classification with a convolutional neural network in the DUNE far detector
• Scalable Deep Convolutional Neural Networks for Sparse, Locally Dense Liquid Argon Time Projection Chamber Data
• Test and characterization of 400 Hamamatsu R5912-MOD photomultiplier tubes for the ICARUS T600 detector
• Design and implementation of the new scintillation light detection system of ICARUS T600
• Reducing model bias in a deep learning classifier using domain adversarial neural networks in the MINERvA experiment

Cited by in corpus (2)

• Improving Robustness of Jet Tagging Algorithms with Adversarial Training
• Contrastive Learning for Robust Representations of Neutrino Data