Deep Learning Transient Detection with VERITAS

TL;DR

This paper presents a deep learning-based transient detection method for VERITAS gamma-ray observatory data, improving detection performance and stability across various observational conditions, demonstrated on a historic blazar flare.

Contribution

The paper introduces a novel deep learning approach for transient detection in VERITAS data that reduces reliance on instrument modeling and adapts to observational variations.

Findings

Effective detection of a blazar flare within minutes

Performance comparable to standard VERITAS analysis

Enhanced stability across different observational conditions

Abstract

Ground-based $\gamma$-ray observatories, such as the VERITAS array of imaging atmospheric Cherenkov telescopes, provide insight into very-high-energy (VHE, $\mathrm{E}>100\,\mathrm{GeV}$) astrophysical transient events. Examples include the evaporation of primordial black holes, gamma-ray bursts and flaring blazars. Identifying such events with a serendipitous location and time of occurrence is difficult. Thus, employing a robust search method becomes crucial. An implementation of a transient detection method based on deep-learning techniques for VERITAS will be presented. This data-driven approach significantly reduces the dependency on the characterization of the instrument response and the modelling of the expected transient signal. The response of the instrument is affected by various factors, such as the elevation of the source and the night sky background. The study of these effects allows enhancing the deep learning method with additional parameters to infer their influences on the data. This improves the performance and stability for a wide range of observational conditions. We illustrate our method for an historic flare of the blazar BL Lac that was detected by VERITAS in October 2016. We find a promising performance for the detection of such a flare in timescales of minutes that compares well with the VERITAS standard analysis.