Active galactic nuclei identification using diffusion-based inpainting of Euclid VIS images

by Dr Grant Stevens (University of Bristol)

Wednesday Jan 21, 2026, 4:00 PM → 5:00 PM Europe/London

Berry Lecture Theatre

Light emission from galaxies exhibit diverse brightness profiles, influenced by factors such as galaxy type, structural features, and interactions with other galaxies. Elliptical galaxies feature more uniform light distributions, while spiral and irregular galaxies have complex, varied light profiles due to their structural heterogeneity and star-forming activity. In addition, galaxies with active galactic nuclei (AGN) feature intense, concentrated emission from gas accretion around supermassive black holes, superimposed on regular galactic light, while quasi-stellar objects (QSOs) represent extreme cases in which AGN emissions dominate their host galaxies. Utilising the spatial resolving power of the Euclid VIS images, we created a diffusion model trained on one million sources, without using any source pre-selection or labels. The model learns to reconstruct light distributions of normal galaxies, since the population is dominated by them. We conditioned the prediction of the central light distribution by masking the central few pixels of each source and reconstructed the light according to the diffusion model. We further used this prediction to identify sources that deviate from this profile by examining the reconstruction error of the few central pixels regenerated in each source’s core. Our approach, solely using VIS imaging, features high completeness compared to traditional methods of AGN and QSO selection, including optical, near-infrared, mid-infrared, and X-rays. We also provide extensive analysis on how state-of-the-art diffusion models handle the varying signal-to-noise and high dynamic ranges found within real world scientific data, a challenge rarely explored in the machine learning literature.

 

 

Join Zoom Meeting
https://cern.zoom.us/j/66923142456?pwd=pVCSHwJ6Mo5SbbNbceRuagSOVPR823.1
Meeting ID: 669 2314 2456
Passcode: 367220