Embedding Reliability for Unsupervised Classification of Gamma Ray Burst progenitors from Prompt Gamma-ray Emission

TL;DR

This paper introduces a statistical method to evaluate the reliability of 2D embeddings of Gamma-Ray Burst data, ensuring trustworthy classifications of GRB progenitors based on prompt emission features.

Contribution

The paper presents a novel application of the scDEED algorithm to assess the reliability of low-dimensional embeddings of GRB data derived from autoencoders and UMAP.

Findings

Over 90% of GRB events are classified as trustworthy in the 2D embedding.

The method provides a statistical measure of embedding reliability for GRB classification.

The approach enhances confidence in low-dimensional representations of complex astrophysical data.

Abstract

We present a statistical method based on scDEED to assess the reliability of a 2D embedding showing a low-dimensional representation of the distribution of Gamma-Ray Bursts (GRBs) detected by the Fermi Gamma-ray Burst Monitor (GBM). The original dataset consists of 12 waterfall plots for each event, which contain key information about the prompt emission of each GRB. The dataset's dimensionality is first reduced to a 30-dimensional latent space using an autoencoder, and subsequently to 2D using UMAP. While the methodology and results are discussed in a previous work (arXiv:2406.03643), here we introduce a statistical approach to evaluate the reliability of the final 2D distribution based on the scDEED algorithm. Our analysis shows that the 2D embedding demonstrates overall good reliability, with more than 90\% of the events classified as trustworthy.