Extracting low energy signals from raw LArTPC waveforms using deep learning techniques -- A proof of concept

TL;DR

This paper demonstrates that deep learning, specifically a 1D-CNN, can effectively extract low-energy signals from raw LArTPC waveforms, surpassing traditional methods and aiding future neutrino experiments.

Contribution

The study introduces a novel application of 1D-CNNs for signal extraction in LArTPC detectors, improving sensitivity to low-energy signals.

Findings

1D-CNN outperforms traditional cut-based methods

Enhanced detection of signals below ADC thresholds

Potential to improve low-energy neutrino physics studies

Abstract

We investigate the feasibility of using deep learning techniques, in the form of a one-dimensional convolutional neural network (1D-CNN), for the extraction of signals from the raw waveforms produced by the individual channels of liquid argon time projection chamber (LArTPC) detectors. A minimal generic LArTPC detector model is developed to generate realistic noise and signal waveforms used to train and test the 1D-CNN, and evaluate its performance on low-level signals. We demonstrate that our approach overcomes the inherent shortcomings of traditional cut-based methods by extending sensitivity to signals with ADC values below their imposed thresholds. This approach exhibits great promise in enhancing the capabilities of future generation neutrino experiments like DUNE to carry out their low-energy neutrino physics programs.