English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

For current and future neutrino oscillation experiments using large LiquidArgon Time Projection Chambers (LAr-TPCs), a key challenge is identifyingneutrino interactions from the pervading cosmic-ray background. Rejection ofsuch background is often possible using traditional cut-based selections, butthis typically requires the prior use of computationally expensivereconstruction algorithms. This work demonstrates an alternative approach ofusing a 3D Submanifold Sparse Convolutional Network trained on low-levelinformation from the scintillation light signal of interactions insideLAr-TPCs. This technique is applied to example simulations from ICARUS, the fardetector of the Short Baseline Neutrino (SBN) program at Fermilab. The resultsof the network, show that cosmic background is reduced by up to 76.3% whilstneutrino interaction selection efficiency remains over 98.9%. We furtherpresent a way to mitigate potential biases from imperfect input simulations byapplying Domain Adversarial Neural Networks (DANNs), for which modifiedsimulated samples are introduced to imitate real data and a small portion ofthem are used for adverserial training. A series of mock-data studies areperformed and demonstrate the effectiveness of using DANNs to mitigate biases,showing neutrino interaction selection efficiency performances significantlybetter than that achieved without the adversarial training.

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