Full-sky Cosmic Microwave Background Foreground Cleaning Using Machine Learning

Abstract

In order to extract cosmological information from observations of the millimeter and submillimeter sky, foreground components must first be removed to produce an estimate of the cosmic microwave background (CMB). We developed a machine-learning approach for doing so for full-sky temperature maps of the millimeter and submillimeter sky. We constructed a Bayesian spherical convolutional neural network architecture to produce a model that captures both spectral and morphological aspects of the foregrounds. Additionally, the model outputs a per-pixel error estimate that incorporates both statistical and model uncertainties. The model was then trained using simulations that incorporated knowledge of these foreground components that was available at the time of the launch of the Planck satellite. On simulated maps, the CMB is recovered with a mean absolute difference of $<4\mu$K over the full sky after masking map pixels with a predicted standard error of $>50\mu$K; the angular power spectrum is also accurately recovered. Once validated with the simulations, this model was applied to Planck temperature observations from its 70GHz through 857GHz channels to produce a foreground-cleaned CMB map at a Healpix map resolution of NSIDE=512. Furthermore, we demonstrate the utility of the technique for evaluating how well different simulations match observations, particularly in regard to the modeling of thermal dust.

arXiv comment10 pages, 6 figures, submitted to ApJ

References in corpus (38)

• The NumPy array: a structure for efficient numerical computation
• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• HEALPix -- a Framework for High Resolution Discretization, and Fast Analysis of Data Distributed on the Sphere
• Nine-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Parameter Results
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Machine learning and the physical sciences
• The Cosmic Linear Anisotropy Solving System (CLASS) II: Approximation schemes
• Planck 2018 results. I. Overview and the cosmological legacy of Planck
• On the Convergence of Adam and Beyond
• Planck 2018 results. V. CMB power spectra and likelihoods
• First Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Foreground Emission
• Extrapolation of Galactic Dust Emission at 100 Microns to CMBR Frequencies Using FIRAS
• Planck 2018 results. IV. Diffuse component separation
• Data Mining and Machine Learning in Astronomy
• Planck 2018 results. III. High Frequency Instrument data processing and frequency maps
• Joint Bayesian component separation and CMB power spectrum estimation
• The pre-launch Planck Sky Model: a model of sky emission at submillimetre to centimetre wavelengths
• Fast estimation of polarization power spectra using correlation functions
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• Foreground component separation with generalised ILC
• Spherical CNNs
• Surveying the reach and maturity of machine learning and artificial intelligence in astronomy
• A needlet ILC analysis of WMAP 7-year data: estimation of CMB temperature map and power spectrum
• Planck 2018 results. II. Low Frequency Instrument data processing
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Simple foreground cleaning algorithm for detecting primordial B-mode polarization of the cosmic microwave background
• SRoll2: an improved mapmaking approach to reduce large-scale systematic effects in the Planck High Frequency Instrument legacy maps
• {\sc CosmoNet}: fast cosmological parameter estimation in non-flat models using neural networks
• Foreground Subtraction of Cosmic Microwave Background Maps using WI-FIT (Wavelet based hIgh resolution Fitting of Internal Templates)
• CMB power spectrum estimation and map reconstruction with the Expectation - Maximization algorithm
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• A Bayesian Framework for Cosmic String Searches in CMB Maps
• Cleaning our own Dust: Simulating and Separating Galactic Dust Foregrounds with Neural Networks
• A 3D model for CO molecular line emission as a potential CMB polarization contaminant
• Concrete Dropout
• Fast Wiener filtering of CMB maps with Neural Networks
• Foreground removal from WMAP 5yr temperature maps using an MLP neural network
• Inpainting via Generative Adversarial Networks for CMB data analysis

Cited by in corpus (30)

• Applications and Techniques for Fast Machine Learning in Science
• CMB/kSZ and Compton-$y$ Maps from 2500 square degrees of SPT-SZ and Planck Survey Data
• Lossless, Scalable Implicit Likelihood Inference for Cosmological Fields
• Machine Learning for Observational Cosmology
• Observational cosmology with Artificial Neural Networks
• ForSE: a GAN based algorithm for extending CMB foreground models to sub-degree angular scales
• A new approach for the statistical denoising of Planck interstellar dust polarization data
• Recovering the CMB Signal with Machine Learning
• Non-Gaussian modelling and statistical denoising of Planck dust polarization full-sky maps using scattering transforms
• MillimeterDL: Deep Learning Simulations of the Microwave Sky
• Likelihood-free Inference with Mixture Density Network
• Reconstructing Patchy Reionization with Deep Learning
• CENN: A fully convolutional neural network for CMB recovery in realistic microwave sky simulations
• A Generative Model of Galactic Dust Emission Using Variational Inference
• Mitigating Foreground Bias to the CMB Lensing Power Spectrum for a CMB-HD Survey
• Inpainting CMB maps using Partial Convolutional Neural Networks
• Recovering Cosmic Microwave Background Polarization Signals with Machine Learning
• Delensing of Cosmic Microwave Background Polarization with machine learning
• Detection of Dipole Modulation in CMB Temperature Anisotropy Maps from WMAP and Planck using Artificial Intelligence
• Estimation of Full Sky Power Spectrum between Intermediate to Large Angular Scales from Partial Sky CMB Anisotropies using Artificial Neural Network
• An Unbiased Estimator of the Full-sky CMB Angular Power Spectrum at Large Scales using Neural Networks
• Lensing reconstruction from the cosmic microwave background polarization with machine learning
• Reconstructing patchy helium reionization using the cosmic microwave background and large-scale structure
• Deep Needlet: A CNN based full sky component separation method in Needlet space
• ParamANN: A Neural Network to Estimate Cosmological Parameters for $\Lambda$CDM Universe Using Hubble Measurements
• Self-supervised component separation for the extragalactic submillimeter sky
• A convolutional-neural-network estimator of CMB constraints on dark matter energy injection
• Reconstruction of full sky CMB $\mathbf{E}$ and $\mathbf{B}$ modes spectra removing $\mathbf{E}$-to-$\mathbf{B}$ leakage from partial sky using deep learning
• Machine Learning-Driven Analysis of kSZ Maps to Predict CMB Optical Depth $\tau$
• Conditional variational autoencoders for cosmological model discrimination and anomaly detection in cosmic microwave background power spectra