Deep Learning for Line Intensity Mapping Observations: Information Extraction from Noisy Maps

Abstract

Line intensity mapping (LIM) is a promising observational method to probe large-scale fluctuations of line emission from distant galaxies. Data from wide-field LIM observations allow us to study the large-scale structure of the universe as well as galaxy populations and their evolution. A serious problem with LIM is contamination by foreground/background sources and various noise contributions. We develop conditional generative adversarial networks (cGANs) that extract designated signals and information from noisy maps. We train the cGANs using 30,000 mock observation maps with assuming a Gaussian noise matched to the expected noise level of NASA's SPHEREx mission. The trained cGANs successfully reconstruct Hα emission from galaxies at a target redshift from observed, noisy intensity maps. Intensity peaks with heights greater than 3.5 σ noise are located with 60 % precision. The one-point probability distribution and the power spectrum are accurately recovered even in the noise-dominated regime. However, the overall reconstruction performance depends on the pixel size and on the survey volume assumed for the training data. It is necessary to generate training mock data with a sufficiently large volume in order to reconstruct the intensity power spectrum at large angular scales. Our deep-learning approach can be readily applied to observational data with line confusion and with noise.

arXiv comment7 pages, 5 figures, accepted for publication in ApJL

References in corpus (10)

• A large Hα survey at z=2.23, 1.47, 0.84 & 0.40: the 11 Gyr evolution of star-forming galaxies from HiZELS
• Galaxy formation in WMAP1 and WMAP7 cosmologies
• Measuring the 3D Clustering of Undetected Galaxies Through Cross Correlation of their Cumulative Flux Fluctuations from Multiple Spectral Lines
• An accurate tool for the fast generation of dark matter halo catalogs
• Spectral Line De-confusion in an Intensity Mapping Survey
• Insights from probability distribution functions of intensity maps
• Phase-Space Spectral Line De-confusion in Intensity Mapping
• Denoising Weak Lensing Mass Maps with Deep Learning
• Tomographic Intensity Mapping versus Galaxy Surveys: Observing the Universe in H-alpha emission with new generation instruments
• Deep learning for intensity mapping observations: Component extraction

Cited by in corpus (13)

• Line-Intensity Mapping: Theory Review
• Noise reduction for weak lensing mass mapping: An application of generative adversarial networks to Subaru Hyper Suprime-Cam first-year data
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• Survey2Survey: A deep learning generative model approach for cross-survey image mapping
• Deep learning reconstruction of three-dimensional galaxy distributions with intensity mapping observations
• Machine learning technique for morphological classification of galaxies from the SDSS. III. Image-based inference of detailed features
• Foreground Removal of CO Intensity Mapping Using Deep Learning
• The power spectrum of galaxies from large to small scales: a line-intensity mapping perspective
• Leveraging cross-correlations and linear covariance-based filtering for line-intensity map reconstructions at linear scales
• Removal of interloper contamination to line-intensity maps using correlations with ancillary tracers of the large-scale structure
• Denoising weak lensing mass maps with diffusion model: systematic comparison with generative adversarial network
• CosmoGLINT: Cosmological Generative Model for Line Intensity Mapping with Transformer