Identification of Extended Emission Gamma-Ray-Bursts Candidates using Machine Learning

TL;DR

This study employs machine learning, specifically t-SNE, to classify gamma-ray bursts and identify new extended emission candidates, enhancing understanding of GRB subgroups using Swift/BAT data.

Contribution

The paper introduces a machine learning approach with t-SNE and noise reduction to classify GRBs and discover new EE candidates based on Swift/BAT data.

Findings

t-SNE effectively separates GRB subgroups

EE GRBs cluster in specific regions of t-SNE maps

Seven new EE GRB candidates identified

Abstract

Gamma-Ray bursts (GRBs) have been traditionally classified based on their duration. The increasing number of extended emission (EE) GRBs, lasting typically more than 2 seconds but with properties similar to those of a short GRBs, challenges the traditional classification criteria. In this work, we use the t-Distributed Stochastic Neighbor Embedding (t-SNE), a machine learning technique, to classify GRBs. We present the results for GRBs observed until July 2022 by the Swift/BAT instrument in all its energy bands. We show the effects of varying the learning rate and perplexity parameters as well as the benefit of pre-processing the data by a non-parametric noise reduction technique FABADA. Consistently with previous works, we show that the t-SNE method separates GRBs in two subgroups. We also show that EE GRBs reported by various authors under different criteria tend to cluster in a few regions of our t-SNE maps, and identify seven new EE GRB candidates by using the gamma-ray data provided by the automatic pipeline of Swift/BAT and the proximity with previously identified EE GRBs.