Exploring Dark Sector Physics in MicroBooNE using Graph Neutral Networks

The MiniBooNE experiment, designed to study neutrino oscillations, detected what has become a longstanding anomaly – an excess of low energy electron-like events from accelerator neutrino interactions. A possible explanation of the anomaly comes from neutrino interactions with nuclei that create heavier, sterile neutrinos. Specifically, we are focusing on sterile neutrino interactions that produce electron-positron pairs. Complementing this is the MicroBooNE experiment, a liquid argon time projection chamber, that can reconstruct events in both two and three dimensions. This reconstruction ability enables us to select dark sector neutrino interactions from all other possible interactions using machine learning techniques such as graph neural networks (GNNs). In this poster, I will present a simulation-based study which will be used to assess the signal to background discrimination power of our GNN in electron-positron pair events.