From Images to Physics: Probabilistic Inference of Galaxy Parameters and Emission Lines via VAE & Normalizing Flows

TL;DR

This paper presents a probabilistic deep learning framework combining VAE and Normalizing Flows to infer galaxy properties and emission line fluxes from imaging data, enabling rapid, non-spectroscopic analysis for large surveys.

Contribution

It introduces a novel VAE-NF model that accurately infers multiple galaxy parameters and emission lines probabilistically from imaging data, including the first estimates of black hole mass from photometry.

Findings

Matches current methods for stellar mass and redshift

Surpasses existing methods for SFR and metallicity

Provides first probabilistic black hole mass estimates from imaging

Abstract

We introduce a Variational Autoencoder (VAE)--Normalizing Flow (NF) framework for rapid probabilistic inference of galaxy properties and emission line fluxes at $z \leq 0.3$ from SDSS \textit{gri} imaging and photometry. Our model probabilistically infers stellar mass, star formation rate (SFR), redshift, gas-phase metallicity, and central black hole mass for a given galaxy. The model accruacy matches current non-spectroscopic methods for stellar mass and redshift, surpasses them for SFR and metallicity, and introduces the first probabilistic central black hole mass estimates from imaging + photometry. It also delivers probabilistic estimates of H$\alpha$, H$\beta$, [N~\textsc{ii}], and [O~\textsc{iii}] emission line fluxes directly from imaging, enabling SFR, metallicity, dust, and AGN/shock diagnostics without spectroscopy. This approach opens new pathways for scalable, physics-informed inference in upcoming surveys such as Roman and Rubin LSST.