Speaker
Description
Redshift measurements of galaxies within galaxy clusters play a crucial role in cosmology and astrophysics, serving as an essential key for cluster identification and related cosmological studies. However, the phase space distribution of cluster galaxies is not yet fully understood, as the observable positions and velocities are subject to line-of-sight projection effects. In this presentation, I will demonstrate how Graph Neural Networks (GNNs) can disentangle the components of galaxy redshift to extract both galaxy peculiar velocity and the internal distance to the host cluster center. Because the physical connections between galaxies and their host clusters can naturally be described as graphs, GNNs provide an effective framework for resolving these phase space projection issues.