HIFlow: Generating Diverse HI Maps and Inferring Cosmology while Marginalizing over Astrophysics using Normalizing Flows
Sultan Hassan, Francisco Villaescusa-Navarro, Benjamin Wandelt, David, N. Spergel, Daniel Angl\'es-Alc\'azar, Shy Genel, Miles Cranmer, Greg L., Bryan, Romeel Dav\'e, Rachel S. Somerville, Michael Eickenberg, Desika, Narayanan, Shirley Ho, Sambatra Andrianomena

TL;DR
HIFlow is a novel normalizing flow-based generative model that produces diverse realistic HI maps conditioned on cosmology, enabling efficient inference and marginalization over astrophysical uncertainties for upcoming large-scale surveys.
Contribution
The paper introduces HIFlow, the first normalizing flow model trained on CAMELS simulations to generate HI maps conditioned on cosmology, capable of marginalizing over astrophysics at the field level.
Findings
HIFlow reproduces the HI power spectrum within a factor of 2.
HIFlow achieves over 90% R-squared in modeling the power spectrum.
The model enables efficient parameter inference by inverting the flow.
Abstract
A wealth of cosmological and astrophysical information is expected from many ongoing and upcoming large-scale surveys. It is crucial to prepare for these surveys now and develop tools that can efficiently extract most information. We present HIFlow: a fast generative model of the neutral hydrogen (HI) maps that is conditioned only on cosmology ( and ) and designed using a class of normalizing flow models, the Masked Autoregressive Flow (MAF). HIFlow is trained on the state-of-the-art simulations from the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project. HIFlow has the ability to generate realistic diverse maps without explicitly incorporating the expected 2D maps structure into the flow as an inductive bias. We find that HIFlow is able to reproduce the CAMELS average and standard deviation HI power spectrum (Pk) within a factor of…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsComputational Physics and Python Applications
