A Demonstration of a Neural Network as a Bridge Between Galaxy Simulations and Surveys

TL;DR

This paper shows that a simple neural network trained on simulated galaxy data can accurately predict stellar masses from photometry, effectively bridging galaxy simulations and observational surveys with minimal complexity.

Contribution

Demonstrates that a basic neural network trained on synthetic data can reliably estimate galaxy stellar masses from photometry, enabling efficient transfer from simulations to real observations.

Findings

Neural network predicts stellar masses with ~0.131 dex scatter.

Model trained on simulations transfers effectively to real GAMA data.

Lightweight model captures key physical information from broad-band photometry.

Abstract

This paper demonstrates that the stellar masses of galaxies in the Galaxy and Mass Assembly (GAMA) survey, originally derived via stellar population synthesis modelling, can be accurately predicted using only their absolute magnitudes and colour indices. A central contribution of this work is the demonstration that this long-standing inference problem can be solved using an exceptionally simple machine-learning model: a fully connected, feed-forward artificial neural network with a single hidden layer. The network is trained exclusively on synthetic galaxies generated by the SHARK semi-analytic model and is shown to transfer effectively to real observations. Across nearly 3.5 dex in stellar mass, the predicted values closely track the GAMA SED-derived masses, with a typical scatter of ~0.131 dex. These results demonstrate that complex deep-learning architectures are not a prerequisite for robust stellar mass estimation, and that simulation-trained, lightweight machine-learning models can capture the dominant physical information encoded in broad-band photometry. The method is further applied to 17,006 GAMA galaxies lacking SED-derived masses, with photometric uncertainties propagated through the network to provide corresponding error estimates on the inferred stellar masses. Overall, this work establishes a computationally efficient and conceptually transparent pathway for simulation-to-observation transfer learning in galaxy evolution studies.