Enhanced Ionization Charge Identification in the Short-Baseline Neutrino Program Neutrino Detectors with Deep Neural Networks

TL;DR

This paper introduces a deep neural network method for improved ionization charge identification in liquid argon neutrino detectors, outperforming traditional algorithms and demonstrating robustness across detector variations.

Contribution

The paper presents a novel DNN-based ROI detection method that leverages full detector readout and cross-plane data, enhancing performance and robustness over traditional thresholding techniques.

Findings

DNN ROI outperforms traditional methods in ROI identification.

DNN ROI improves high-level reconstruction metrics.

Method is more robust against detector variations.

Abstract

We present a deep neural net-based region of interest detection method (DNN ROI) for signal processing in the liquid argon time projection chambers of the Short-Baseline Neutrino (SBN) Program, SBND and ICARUS. DNN ROI addresses limitations of the traditional wire-by-wire thresholding algorithm by leveraging the full two-dimensional detector readout and cross-plane matching information. To account for detector performance variations, we explore training with augmented samples. We find that DNN ROI outperforms the traditional method in both low-level ROI identification performance and high-level reconstruction metrics for high-energy cosmic and accelerator neutrino interaction products, while also being more robust against detector variations, with or without sample augmentation.