22 March 2021
Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
Researchers at DARK have developed a novel AI-based tool to infer the dynamical masses of galaxy clusters, which are the most massive gravitationally bound systems in the Universe. The proposed framework constitutes the first optimal machine learning-based exploitation of the information content of the full 3D projected phase-space distribution of galaxy clusters, as characterised by the galaxy positions in the sky and their line-of-sight velocities. This new technique, as a result, substantially outperforms classical mass estimators based on scaling relations and other recently proposed deep learning mass estimation methods in terms of precision.