Litcius/Paper detail

A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys

Michelle Ntampaka, Daniel J. Eisenstein, Sihan Yuan, Lehman H. Garrison

2020The Astrophysical Journal44 citationsDOIOpen Access PDF

Abstract

Abstract We present a deep machine learning (ML)–based technique for accurately determining σ 8 and Ω m from mock 3D galaxy surveys. The mock surveys are built from the AbacusCosmos suite of N -body simulations, which comprises 40 cosmological volume simulations spanning a range of cosmological parameter values, and we account for uncertainties in galaxy formation scenarios through the use of generalized halo occupation distributions (HODs). We explore a trio of ML models: a 3D convolutional neural network (CNN), a power spectrum–based fully connected network, and a hybrid approach that merges the two to combine physically motivated summary statistics with flexible CNNs. We describe best practices for training a deep model on a suite of matched-phase simulations, and we test our model on a completely independent sample that uses previously unseen initial conditions, cosmological parameters, and HOD parameters. Despite the fact that the mock observations are quite small (∼0.07 h −3 Gpc 3 ) and the training data span a large parameter space (six cosmological and six HOD parameters), the CNN and hybrid CNN can constrain estimates of σ 8 and Ω m to ∼3% and ∼4%, respectively.

Topics & Concepts

PhysicsGalaxyHaloAstrophysicsDeep learningConvolutional neural networkRedshiftParameter spaceSuiteGalaxy formation and evolutionArtificial intelligenceRange (aeronautics)Artificial neural networkCosmologyGalactic haloSatellite galaxyDeep neural networksMachine learningSpace (punctuation)Observational cosmologyCosmological modelGalaxies: Formation, Evolution, PhenomenaAstronomy and Astrophysical ResearchGamma-ray bursts and supernovae
A Hybrid Deep Learning Approach to Cosmological Constraints from Galaxy Redshift Surveys | Litcius