Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach

• URL: http://arxiv.org/abs/2302.12378v1
• Date: Fri, 24 Feb 2023 00:49:43 GMT
• Title: Cosmic Microwave Background Recovery: A Graph-Based Bayesian Convolutional Network Approach
• Authors: Jadie Adams, Steven Lu, Krzysztof M. Gorski, Graca Rocha, Kiri L. Wagstaff
• Abstract summary: We employ deep learning as a data-driven approach to CMB cleaning from multi-frequency full-sky maps. We develop a graph-based Bayesian convolutional neural network based on the U-Net architecture that predicts cleaned CMB with pixel-wise uncertainty estimates. We show that our model accurately recovers the cleaned CMB sky map and resulting angular power spectrum while identifying regions of uncertainty.
• Score: 2.689611937246938
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The cosmic microwave background (CMB) is a significant source of knowledge about the origin and evolution of our universe. However, observations of the CMB are contaminated by foreground emissions, obscuring the CMB signal and reducing its efficacy in constraining cosmological parameters. We employ deep learning as a data-driven approach to CMB cleaning from multi-frequency full-sky maps. In particular, we develop a graph-based Bayesian convolutional neural network based on the U-Net architecture that predicts cleaned CMB with pixel-wise uncertainty estimates. We demonstrate the potential of this technique on realistic simulated data based on the Planck mission. We show that our model accurately recovers the cleaned CMB sky map and resulting angular power spectrum while identifying regions of uncertainty. Finally, we discuss the current challenges and the path forward for deploying our model for CMB recovery on real observations.

Related papers

• Influence Maximization via Graph Neural Bandits [54.45552721334886]
  We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced. We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced.
  arXiv  Detail & Related papers  (2024-06-18T17:54:33Z)
• Super-Resolution of BVOC Emission Maps Via Domain Adaptation [17.819699053848197]
  SuperResolution (SR) methods based on Deep Learning (DL) have been proposed, leveraging data from numerical simulations for their training process. In our work, we aim at super-resolving low resolution emission maps derived from satellite observations by leveraging the information of emission maps obtained through numerical simulations. We investigate the effectiveness of Domain Adaptation (DA) strategies at different stages by systematically varying the number of simulated and observed emissions used.
  arXiv  Detail & Related papers  (2023-06-22T10:59:15Z)
• Neural FIM for learning Fisher Information Metrics from point cloud data [71.07939200676199]
  We propose neural FIM, a method for computing the Fisher information metric (FIM) from point cloud data. We demonstrate its utility in selecting parameters for the PHATE visualization method as well as its ability to obtain information pertaining to local volume illuminating branching points and cluster centers embeddings of a toy dataset and two single-cell datasets of IPSC reprogramming and PBMCs (immune cells)
  arXiv  Detail & Related papers  (2023-06-01T17:36:13Z)
• Pixelated Reconstruction of Foreground Density and Background Surface Brightness in Gravitational Lensing Systems using Recurrent Inference Machines [116.33694183176617]
  We use a neural network based on the Recurrent Inference Machine to reconstruct an undistorted image of the background source and the lens mass density distribution as pixelated maps. When compared to more traditional parametric models, the proposed method is significantly more expressive and can reconstruct complex mass distributions.
  arXiv  Detail & Related papers  (2023-01-10T19:00:12Z)
• Bayesian Structure Learning with Generative Flow Networks [85.84396514570373]
  In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) from data. Recently, a class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling. We show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs.
  arXiv  Detail & Related papers  (2022-02-28T15:53:10Z)
• Deep Learning Based Cloud Cover Parameterization for ICON [55.49957005291674]
  We train NN based cloud cover parameterizations with coarse-grained data based on realistic regional and global ICON simulations. Globally trained NNs can reproduce sub-grid scale cloud cover of the regional simulation. We identify an overemphasis on specific humidity and cloud ice as the reason why our column-based NN cannot perfectly generalize from the global to the regional coarse-grained data.
  arXiv  Detail & Related papers  (2021-12-21T16:10:45Z)
• ME-PCN: Point Completion Conditioned on Mask Emptiness [50.414383063838336]
  Main-stream methods predict missing shapes by decoding a global feature learned from the input point cloud. We present ME-PCN, a point completion network that leverages emptiness' in 3D shape space.
  arXiv  Detail & Related papers  (2021-08-18T15:02:27Z)
• An Unbiased Estimator of the Full-sky CMB Angular Power Spectrum using Neural Networks [0.0]
  We produce unbiased predictions of the full-sky angular power spectrum and the underlying theoretical power spectrum using neural networks. Our predictions are also uncorrelated to a large extent.
  arXiv  Detail & Related papers  (2021-02-08T16:30:31Z)
• Reconstructing Patchy Reionization with Deep Learning [0.0]
  We describe a convolutional neural network, ResUNet-CMB, that is capable of the simultaneous reconstruction of two sources of secondary CMB anisotropies. We show that the ResUNet-CMB network significantly outperforms the quadratic estimator at low noise levels.
  arXiv  Detail & Related papers  (2021-01-04T19:58:28Z)
• Foreground model recognition through Neural Networks for CMB B-mode observations [0.0]
  In particular, we have focused our analysis on low frequency foregrounds relevant for polarization observation. We have implemented and tested our approach on a set of simulated maps corresponding to the frequency coverage and sensitivity represented by future satellite and low frequency ground based probes. The NN efficiency in recognizing the right parametrization of foreground emission in different sky regions reaches an accuracy of about $90%$.
  arXiv  Detail & Related papers  (2020-03-04T19:00:02Z)
• CosmoVAE: Variational Autoencoder for CMB Image Inpainting [4.69377041192659]
  The noise of the CMB map has a significant impact on the estimation precision for cosmological parameters. In this paper, we propose a deep learning-based variational autoencoder to restore the missing observations of the CMB map. The proposed model achieves state of the art performance for Planck textttCommander 2018 CMB map inpainting.
  arXiv  Detail & Related papers  (2020-01-31T03:54:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.