Supervised Extraction of the Thermal Sunyaev$-$Zel'dovich Effect with a Three-Dimensional Convolutional Neural Network

Abstract

The thermal Sunyaev$-$Zel'dovich (SZ) effect offers a unique probe of the hot and diffuse universe that could help close the missing baryon problem. Traditional extractions of the SZ effect, however, exhibit systematic noise that may lead to unreliable results. In this work, we provide an alternative solution using a three-dimensional Attention Nested U-Net trained end-to-end with supervised learning. Our labeled data consists of simulated SZ signals injected into $\text{Planck}$ frequency maps, allowing our model to learn how to extract SZ signals in the presence of realistic noise. We implement a curriculum learning scheme that gradually exposed the model to weaker SZ signals. The absence/presence of curriculum learning significantly impacted the amount of bias and variance present in the reconstructed SZ signal. The results from our method were comparable to those from the popular $\text{needlet internal linear combination}$ (NILC) method when evaluated on simulated data as well as real-world SZ signals. We conclude by discussing future avenues for advancing machine learning extractions of SZ signals.

16 pages, 6 figures, 2 tables, Accepted by ApJ

References in corpus (21)

• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• The universal galaxy cluster pressure profile from a representative sample of nearby systems (REXCESS) and the Y_SZ-M_500 relation
• The Sunyaev-Zel'dovich Effect
• The MCXC: a Meta-Catalogue of X-ray detected Clusters of galaxies
• The Baryon Census in a Multiphase Intergalactic Medium: 30% of the Baryons May Still Be Missing
• The Search for the Missing Baryons at Low Redshift
• Planck intermediate results. LVII. Joint Planck LFI and HFI data processing
• A full sky, low foreground, high resolution CMB map from WMAP
• Component separation methods for the Planck mission
• The Python Sky Model: software for simulating the Galactic microwave sky
• Catalog Extraction in SZ Cluster Surveys: a matched filter approach
• Simulations of the Microwave Sky
• CMB and SZ effect separation with Constrained Internal Linear Combinations
• Planck 2015 results. XXIII. The thermal Sunyaev-Zeldovich effect--cosmic infrared background correlation
• SZ and CMB reconstruction using Generalized Morphological Component Analysis
• The Cosmic Thermal History Probed by Sunyaev-Zeldovich Effect Tomography
• Planck intermediate results. XL. The Sunyaev-Zeldovich signal from the Virgo cluster
• BeyondPlanck III. Commander3
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Reconstructing Cosmic Polarization Rotation with ResUNet-CMB
• Data driven foreground clustering approach to component separation in multifrequency CMB experiments: A new Planck CMB map