From Simulations to Surveys: Domain Adaptation for Galaxy Observations

Kaley Brauer, Aditya Prasad Dash, Meet J. Vyas, Ahmed Salim, Stiven Briand Massala
11/23/2025
astro-ph.GAcs.LG

No official code found. Best implementation: ahmedsalim3/galaxy-da (3 stars, MIT, last commit 2025-11-26).

Abstract

Large photometric surveys will image billions of galaxies, but we currently lack quick, reliable automated ways to infer their physical properties like morphology, stellar mass, and star formation rates. Simulations provide galaxy images with ground-truth physical labels, but domain shifts in PSF, noise, backgrounds, selection, and label priors degrade transfer to real surveys. We present a preliminary domain adaptation pipeline that trains on simulated TNG50 galaxies and evaluates on real SDSS galaxies with morphology labels (elliptical/spiral/irregular). We train three backbones (CNN, $E(2)$-steerable CNN, ResNet-18) with focal loss and effective-number class weighting, and a feature-level domain loss $L_D$ built from GeomLoss (entropic Sinkhorn OT, energy distance, Gaussian MMD, and related metrics). We show that a combination of these losses with an OT-based "top_$k$ soft matching" loss that focuses $L_D$ on the worst-matched source-target pairs can further enhance domain alignment. With Euclidean distance, scheduled alignment weights, and top-$k$ matching, target accuracy (macro F1) rises from $\sim$46% ($\sim$30%) at no adaptation to $\sim$87% ($\sim$62.6%), with a domain AUC near 0.5, indicating strong latent-space mixing.

View on arXivView PDF

Code Implementations(1)

ahmedsalim3/galaxy-daCommunity75%
MIT

Source code for the paper titled "From Simulations to Surveys: Domain Adaptation for Galaxy Observations"

31Shell, PythonAug 9, 202510 months agoMIT

Similar Papers

Domain Adaptive Graph Neural Networks for Constraining Cosmological Parameters Across Multiple Data Sets

83% match2023

From Galaxy Zoo DECaLS to BASS/MzLS: detailed galaxy morphology classification with unsupervised domain adaption

83% match1 repo12024

Combining datasets with different ground truths using Low-Rank Adaptation to generalize image-based CNN models for photometric redshift prediction

83% match1 repo2026

GalaxiesML: a dataset of galaxy images, photometry, redshifts, and structural parameters for machine learning

82% match1 repo82024

Dark Energy Survey Year 3 results: Simulation-based wCDM inference from weak lensing and galaxy clustering maps with deep learning. I. Analysis design

81% match2025

Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantification

81% match1 repo2024

Cite this paper

@article{brauer2025from,
  title  = {From Simulations to Surveys: Domain Adaptation for Galaxy Observations},
  author = {Kaley Brauer and Aditya Prasad Dash and Meet J. Vyas and Ahmed Salim and Stiven Briand Massala},
  year   = {2025},
  eprint = {2511.18590},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.18590v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.18590.svg)](https://codeofpaper.com/paper/2511.18590)

Discussion