KilonovAE: Exploring Kilonova Spectral Features with Autoencoders

TL;DR

This paper uses autoencoders and Bayesian clustering on simulated kilonova spectra to identify key absorption features and relate them to ejecta properties, aiding future spectral analysis.

Contribution

It introduces a machine learning framework combining autoencoders and clustering to analyze kilonova spectra and interpret their physical properties.

Findings

Strong absorption lines of Sr II, Y II, Zr I-II identified in synthetic spectra.

Lanthanide features prominent at low electron fractions (Ye < 0.25).

Spectral clustering reveals diversity and common features among simulated kilonovae.

Abstract

Kilonovae are likely a key site of heavy r-process element production in the Universe, and their optical/infrared spectra contain insights into both the properties of the ejecta and the conditions of the r-process. However, the event GW170817/AT2017gfo is the only kilonova so far with well-observed spectra. To understand the diversity of absorption features that might be observed in future kilonovae spectra, we use the TARDIS Monte Carlo radiative transfer code to simulate a suite of optical spectra spanning a wide range of kilonova ejecta properties and r-process abundance patterns. To identify the most common and prominent absorption lines, we perform dimensionality reduction using an autoencoder, and we find spectra clusters in the latent space representation using a Bayesian Gaussian Mixture model. Our synthetic kilonovae spectra commonly display strong absorption by strontium Sr II, yttrium Y II, and zirconium Zr I - II, with strong lanthanide contributions at low electron fractions (Ye < 0.25). When a new kilonova is observed, our machine learning framework will provide context on the dominant absorption lines and key ejecta properties, helping to determine where this event falls within the larger 'zoo' of kilonovae spectra.