Foreground Removal of CO Intensity Mapping Using Deep Learning
arXiv:2212.14712 · doi:10.1093/mnras/stad563
Abstract
Line intensity mapping (LIM) is a promising probe to study star formation, the large-scale structure of the Universe, and the epoch of reionization (EoR). Since carbon monoxide (CO) is the second most abundant molecule in the Universe except for molecular hydrogen , it is suitable as a tracer for LIM surveys. However, just like other LIM surveys, CO intensity mapping also suffers strong foreground contamination that needs to be eliminated for extracting valuable astrophysical and cosmological information. In this work, we take CO(=1-0) emission line as an example to investigate whether deep learning method can effectively recover the signal by removing the foregrounds. The CO(1-0) intensity maps are generated by N-body simulations considering CO luminosity and halo mass relation, and we discuss two cases with median and low CO signals by comparing different relations. We add foregrounds generated from real observations, including thermal dust, spinning dust, free-free, synchrotron emission and CMB anisotropy. The beam with sidelobe effect is also considered. Our deep learning model is built upon ResUNet, which combines image generation algorithm UNet with the state-of-the-art architecture of deep learning, ResNet. The principal component analysis (PCA) method is employed to preprocess data before feeding it to the ResUNet. We find that, in the case of low instrumental noise, our UNet can efficiently reconstruct the CO signal map with correct line power spectrum by removing the foregrounds and recovering PCA signal loss and beam effects. Our method also can be applied to other intensity mappings like neutral hydrogen 21cm surveys.
arXiv comment12 pages, 12 figures, 2 tables. Accepted for publication in MNRAS
References in corpus (58)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Conditional Generative Adversarial Nets
- Planck 2013 results. XVI. Cosmological parameters
- Simulating the joint evolution of quasars, galaxies and their large-scale distribution
- Deep Residual Learning for Image Recognition
- Generative Adversarial Networks
- Large scale bias and the peak background split
- ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
- Cool Gas in High Redshift Galaxies
- MultiDark simulations: the story of dark matter halo concentrations and density profiles
- Different star formation laws for disks versus starbursts at low and high redshifts
- The Herschel PEP/HerMES Luminosity Function. I: Probing the Evolution of PACS selected Galaxies to z~4
- The evolution of the dust temperatures of galaxies in the SFR plane up to
- The Python Sky Model: software for simulating the Galactic microwave sky
- Intensity Mapping with Carbon Monoxide Emission Lines and the Redshifted 21 cm Line
- Intensity Mapping of the [CII] Fine Structure Line during the Epoch of Reionization
- Star formation relations and CO SLEDs across the J-ladder and redshift
- Line-Intensity Mapping: 2017 Status Report
- Blind foreground subtraction for intensity mapping experiments
- Measuring the 3D Clustering of Undetected Galaxies Through Cross Correlation of their Cumulative Flux Fluctuations from Multiple Spectral Lines
- AI-assisted super-resolution cosmological simulations
- CCAT-prime Collaboration: Science Goals and Forecasts with Prime-Cam on the Fred Young Submillimeter Telescope
- COPSS II: The Molecular Gas Content of Ten Million Cubic Megaparsecs at
- Molecular gas content in strongly-lensed z~1.5-3 star-forming galaxies with low IR luminosities
- Intensity Mapping of Lyman-alpha Emission During the Epoch of Reionization
- Fast cosmic web simulations with generative adversarial networks
- Intensity Mapping across Cosmic Times with the Lyman-Alpha Line
- Intensity mapping of [CII] from early galaxies
- Probing Reionization with Intensity Mapping of Molecular and Fine Structure Lines
- On Removing Interloper Contamination from Intensity Mapping Power Spectrum Measurements
- Intensity mapping of molecular gas during cosmic reionization
- Super-resolution emulator of cosmological simulations using deep physical models
- Cosmology with intensity mapping techniques using atomic and molecular lines
- An Intensity Mapping Detection of Aggregate CO Line Emission at 3 mm
- COMAP Early Science: I. Overview
- Foreground contamination in Ly-alpha intensity mapping during the epoch of reionization
- deep21: a Deep Learning Method for 21cm Foreground Removal
- Primary beam effects of radio astronomy antennas -- II. Modelling the MeerKAT L-band beam
- Deep observations of CO line emission from star-forming galaxies in a cluster candidate at z=1.5
- Constraining the CO intensity mapping power spectrum at intermediate redshifts
- Classifying the Large Scale Structure of the Universe with Deep Neural Networks
- Hi intensity mapping with MeerKAT: Primary beam effects on foreground cleaning
- Demonstrating the Feasibility of Line Intensity Mapping Using Mock Data of Galaxy Clustering from Simulations
- Intensity mapping of H-alpha, H-beta, [OII] and [OIII] lines at z<5
- Impact of Simulated 1/f Noise for HI Intensity Mapping Experiments
- First Results from COPSS: The CO Power Spectrum Survey
- Measuring Galaxy Clustering and the Evolution of [CII] Mean Intensity with far-IR Line Intensity Mapping During 0.5 < z < 1.5
- From Dark Matter to Galaxies with Convolutional Networks
- COMAP Early Science: V. Constraints and Forecasts at
- COMAP Early Science: VII. Prospects for CO Intensity Mapping at Reionization
- Eliminating Primary Beam Effect in Foreground Subtraction of Neutral Hydrogen Intensity Mapping Survey with Deep Learning
- Cosmological constraints from line intensity mapping with interlopers
- COMAP Early Science: IV. Power Spectrum Methodology and Results
- The Electromagnetic Characteristics of the Tianlai Cylindrical Pathfinder Array
- Probing the Pre-Reionization Epoch with Molecular Hydrogen Intensity Mapping
- Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps
- Forecasting the Cross-Correlation of the CSST galaxy survey with the FAST HI Intensity Map
- Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations