Galaxy Merger Reconstruction with Equivariant Graph Normalizing Flows

TL;DR

This paper introduces a novel generative graph model based on equivariant normalizing flows to accurately reconstruct galaxy merger histories, capturing key properties like masses and redshifts, and enabling advanced inference tasks.

Contribution

The work presents a new graph-based generative model for galaxy mergers that effectively recovers progenitor distributions and supports downstream astrophysical analyses.

Findings

Successfully recovers progenitor distributions including masses and redshifts

Enables likelihood-free inference and anomaly detection in galaxy data

Demonstrates robustness in modeling galaxy merger histories

Abstract

A key yet unresolved question in modern-day astronomy is how galaxies formed and evolved under the paradigm of the $\Lambda$CDM model. A critical limiting factor lies in the lack of robust tools to describe the merger history through a statistical model. In this work, we employ a generative graph network, E(n) Equivariant Graph Normalizing Flows Model. We demonstrate that, by treating the progenitors as a graph, our model robustly recovers their distributions, including their masses, merging redshifts and pairwise distances at redshift z=2 conditioned on their z=0 properties. The generative nature of the model enables other downstream tasks, including likelihood-free inference, detecting anomalies and identifying subtle correlations of progenitor features.