Convolutional Neural Networks in LArTPCs: Using AI to Find Neutrinos in MicroBooNE

MicroBooNE, a Liquid Argon Time Projection Chamber (LArTPC) located in the $\nu_{\mu}$-dominated Booster Neutrino Beam at Fermilab, has been studying $\nu_{e}$ charged-current (CC) interaction rates to shed light on the measured MiniBooNE low energy excess. The LArTPC technology pioneered by MicroBooNE provides the capability to image neutrino interactions with mm-scale precision. Computer vision techniques such as Convolutional Neural Networks (CNNs) can be used to process these images and aid in selecting $\nu_{e}$-CC and other rare signals from large cosmic and beam-induced neutrino backgrounds. I will provide an introduction to LArTPCs and CNNs, outline the prior use of CNNs and similar tools in neutrino experiments, and present a new CNN-based event reconstruction framework to identify neutrino interactions in MicroBooNE. I will show that these techniques have the potential to increase MicroBooNE's $\nu_{e}$-CC selection efficiency and improve the sensitivity of future analyses, both in MicroBooNE and other current and planned LArTPC neutrino experiments.