Galactic Alchemy: Deep Learning Map-to-Map Translation in Hydrodynamical Simulations

TL;DR

This paper explores deep learning models for translating various galactic properties in simulations, demonstrating high accuracy for some mappings and highlighting challenges in others, with implications for astrophysical modeling.

Contribution

It systematically compares GANs and diffusion models for multi-domain galaxy map translation, introducing physics-aware metrics and optimizing architectures for astrophysical fidelity.

Findings

GANs perform competitively with diffusion models at lower computational cost

High fidelity achieved in gas to dark matter and astro-chemical mappings

Weakly constrained tasks like gas to stellar mass remain challenging

Abstract

We present the first systematic study of multi-domain map-to-map translation in galaxy formation simulations, leveraging deep generative models to predict diverse galactic properties. Using high-resolution magneto-hydrodynamical simulation data, we compare conditional generative adversarial networks and diffusion models under unified preprocessing and evaluation, optimizing architectures and attention mechanisms for physical fidelity on galactic scales. Our approach jointly addresses seven astrophysical domains - including dark matter, gas, neutral hydrogen, stellar mass, temperature, and magnetic field strength - while introducing physics-aware evaluation metrics that quantify structural realism beyond standard computer vision measures. We demonstrate that translation difficulty correlates with physical coupling, achieving near-perfect fidelity for mappings from gas to dark matter and mappings involving astro-chemical components such as total gas to HI content, while identifying fundamental challenges in weakly constrained tasks such as gas to stellar mass mappings. Our results establish GAN-based models as competitive counterparts to state-of-the-art diffusion approaches at a fraction of the computational cost (in training and inference), paving the way for scalable, physics-aware generative frameworks for forward modelling and observational reconstruction in the SKA era.