2020/06/30 by Matthew Ho, Arya Farahi, Markus Michael Rau +1
Computer Science · Mathematics · Physics and Astronomy · #Advanced Statistical Methods and Models #Algorithm #Artificial intelligence #Bayesian inference #Bayesian probability #Cluster (spacecraft) #Computer science #Context (archaeology) #Convolutional neural network #Galaxies: Formation, Evolution, Phenomena #Gaussian Processes and Bayesian Inference #Inference #astro-ph.CO
paper · pdf · doi:10.3847/1538-4357/abd101
published as 2021 ApJ, 908, 204H · 15 pages, 5 figures. 3 tables, accepted for publication at ApJ
openalex created_date 2020/07/02 · openalex publication_date 2021/02/01 · arxiv created 2021/03/14 · arxiv updated 2021/03/16 · openalex updated_date 2026/08/06
Abstract We study methods for reconstructing Bayesian uncertainties on dynamical mass estimates of galaxy clusters using convolutional neural networks (CNNs). We discuss the statistical background of approximate Bayesian neural networks and demonstrate how variational inference techniques can be used to perform computationally tractable posterior estimation for a variety of deep neural architectures. We explore how various model designs and statistical assumptions impact prediction accuracy and uncertainty reconstruction in the context of cluster mass estimation. We measure the quality of our model posterior recovery using a mock cluster observation catalog derived from the MultiDark simulation and UniverseMachine catalog. We show that approximate Bayesian CNNs produce highly accurate dynamical cluster mass posteriors. These model posteriors are log-normal in cluster mass and recover 68% and 90% confidence intervals to within 1% of their measured value. We note how this rigorous modeling of dynamical mass posteriors is necessary for using cluster abundance measurements to constrain cosmological parameters.