Simulation-based inference of the 2D ex-situ stellar mass fraction distribution of galaxies using variational autoencoders

TL;DR

This paper introduces a novel probabilistic deep learning approach using variational autoencoders and normalizing flows to infer the 2D ex-situ stellar mass distribution of galaxies from observable data, achieving about 10% accuracy per pixel.

Contribution

It is the first to use a conditional variational autoencoder with normalizing flows for inferring 2D ex-situ stellar mass maps from observable galaxy properties.

Findings

Achieves ~10% mean error in posterior estimates per pixel.

Normalizing flow improves reconstruction accuracy.

Uncertainty quantification is enabled by the probabilistic model.

Abstract

Galaxies grow through star formation (in-situ) and accretion (ex-situ) of other galaxies. Reconstructing the relative contribution of these two growth channels is crucial for constraining the processes of galaxy formation in a cosmological context. In this on-going work, we utilize a conditional variational autoencoder along with a normalizing flow - trained on a state-of-the-art cosmological simulation - in an attempt to infer the posterior distribution of the 2D ex-situ stellar mass distribution of galaxies solely from observable two-dimensional maps of their stellar mass, kinematics, age and metallicity. Such maps are typically obtained from large Integral Field Unit Surveys such as MaNGA. We find that the average posterior provides an estimate of the resolved accretion histories of galaxies with a mean ~10% error per pixel. We show that the use of a normalizing flow to conditionally sample the latent space results in a smaller reconstruction error. Due to the probabilistic nature of our architecture, the uncertainty of our predictions can also be quantified. To our knowledge, this is the first attempt to infer the 2D ex-situ fraction maps from observable maps.