Morphological evolution of galaxies with deep learning

Research output: ThesisDoctoral Thesis

115 Downloads (Pure)


Understanding the changes in galaxy morphology over time can yield important insights into the physics behind galaxy evolution. In this thesis, I adopt a deep learning approach to morphological classification. I develop a new suite of CNNs to rapidly and accurately classify galaxy morphologies. I apply these models to classify tens of thousands of galaxies in several datasets across observational surveys and simulations, analysing the evolution of barred galaxies in EAGLE, the growth of lenticular galaxies over time in COSMOS, and the kinematics of different morphologies in SAMI. I also develop an image segmentation model capable of analysing galaxy bars.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • The University of Western Australia
  • Bekki, Kenji, Supervisor
  • Groves, Brent, Supervisor
Thesis sponsors
Award date6 Jun 2023
Publication statusUnpublished - 2023


Dive into the research topics of 'Morphological evolution of galaxies with deep learning'. Together they form a unique fingerprint.

Cite this