VAE-based latent-space classification of RNO-G data

TL;DR

This paper presents a novel method using a variational autoencoder's latent space to classify and separate different noise and signal classes in RNO-G neutrino detection data, aiding in background discrimination.

Contribution

It introduces a VAE-based approach to classify noise and signal types in radio neutrino data, improving background separation in RNO-G measurements.

Findings

Automatically detects and separates multiple event classes.

Qualitatively distinguishes physical wind signals from other noise.

Effective in both noisy and silent station data.

Abstract

The Radio Neutrino Observatory in Greenland (RNO-G) is a radio-based ultra-high energy neutrino detector located at Summit Station, Greenland. It is still being constructed, with 7 stations currently operational. Neutrino detection works by measuring Askaryan radiation produced by neutrino-nucleon interactions. A neutrino candidate must be found amidst other backgrounds which are recorded at much higher rates -- including cosmic-rays and anthropogenic noise -- the origins of which are sometimes unknown. Here we describe a method to classify different noise classes using the latent space of a variational autoencoder. The latent space forms a compact representation that makes classification tractable. We analyze data from a noisy and a silent station. The method automatically detects and allows us to qualitatively separate multiple event classes, including physical wind-induced signals, for both the noisy and the quiet station.