6–10 Jul 2026
University of the Western Cape
Africa/Johannesburg timezone
**Tours now open!** Registration is now closed - All registration payments are due before 23:39 SAST on 26 June.

Automating Galaxy Classification with Unsupervised Machine Learning

8 Jul 2026, 16:20
1h 20m
Great Hall ( University of the Western Cape)

Great Hall

University of the Western Cape

Poster Presentation Track D - Astrophysics & Space Science Poster Session 2

Speaker

Kirsten Elliott (University of Western Cape)

Description

Self-supervised learning offers a powerful way to analyse large astronomical image datasets without relying on labelled training samples. Mohale & Lochner (2024) demonstrated this by fine-tuning a ResNet-18 model with the Bootstrap Your Own Latent (BYOL) framework to produce 512-dimensional feature representations for galaxies in the Dark Energy Camera Legacy Survey (DECaLS) survey. After reducing these features via Principal Component Analysis (PCA), they used Bayesian Gaussian Mixture Models (BGMM) to test whether the representations could recover broad morphological structure without labels, demonstrating that self-supervised features contain useful information for separating galaxy types.

In this project, I reproduce their representation-learning experiment and evaluate how useful these features are for unsupervised morphology studies. I apply a more efficient clustering strategy, MiniBatchKMeans to test whether the representations can separate basic morphological classes. To measure this, I construct a high-confidence labelled sample from the Galaxy Zoo: DECaLS catalogue and compare the cluster assignments with the volunteer classifications. I further assess the structure of the feature space using Uniform Manifold Approximation and Projection (UMAP) projections and examine the stability of the cluster assignments across repeated runs.

The results show that the PCA reduced BYOL-derived features are able to distinguish between round ellipticals, spirals, and edge-on galaxies. This demonstrates that self-supervised features provide a promising and scalable basis for unsupervised galaxy morphology analysis in future large surveys.

Apply for student award at which level: MSc
Consent on use of personal information: Abstract Submission Yes, I ACCEPT

Author

Kirsten Elliott (University of Western Cape)

Presentation materials

There are no materials yet.