Classifying CMB time-ordered data through deep neural networks

Abstract

The Cosmic Microwave Background (CMB) has been measured over a wide range of multipoles. Experiments with arc-minute resolution like the Atacama Cosmology Telescope (ACT) have contributed to the measurement of primary and secondary anisotropies, leading to remarkable scientific discoveries. Such findings require careful data selection in order to remove poorly-behaved detectors and unwanted contaminants. The current data classification methodology used by ACT relies on several statistical parameters that are assessed and fine-tuned by an expert. This method is highly time-consuming and band or season-specific, which makes it less scalable and efficient for future CMB experiments. In this work, we propose a supervised machine learning model to classify detectors of CMB experiments. The model corresponds to a deep convolutional neural network. We tested our method on real ACT data, using the 2008 season, 148 GHz, as training set with labels provided by the ACT data selection software. The model learns to classify time-streams starting directly from the raw data. For the season and frequency considered during the training, we find that our classifier reaches a precision of 99.8%. For 220 and 280 GHz data, season 2008, we obtained 99.4% and 97.5% of precision, respectively. Finally, we performed a cross-season test over 148 GHz data from 2009 and 2010 for which our model reaches a precision of 99.8% and 99.5%, respectively. Our model is about 10x faster than the current pipeline, making it potentially suitable for real-time implementations.

arXiv comment9 pages, 6 figures

References in corpus (26)

• Auto-Encoding Variational Bayes
• Decoupled Weight Decay Regularization
• Deep Residual Learning for Image Recognition
• The Simons Observatory: Science goals and forecasts
• Recent Trends in Deep Learning Based Natural Language Processing
• Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Xception: Deep Learning with Depthwise Separable Convolutions
• CMB-S4 Science Book, First Edition
• Detection of the Power Spectrum of Cosmic Microwave Background Lensing by the Atacama Cosmology Telescope
• The South Pole Telescope
• The Atacama Cosmology Telescope: The Receiver and Instrumentation
• Evidence of Galaxy Cluster Motions with the Kinematic Sunyaev-Zel'dovich Effect
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• ACTPol: A polarization-sensitive receiver for the Atacama Cosmology Telescope
• DeepSphere: Efficient spherical Convolutional Neural Network with HEALPix sampling for cosmological applications
• The Atacama Cosmology Telescope: Data Characterization and Map Making
• DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
• Mapping H-band Scattered Light Emission in the Mysterious SR21 Transitional Disk
• The Impact of Atmospheric Fluctuations on Degree-scale Imaging of the Cosmic Microwave Background
• Deep multi-survey classification of variable stars
• Convolutional Neural Networks on the HEALPix sphere: a pixel-based algorithm and its application to CMB data analysis
• An autoencoder of stellar spectra and its application in automatically estimating atmospheric parameters
• Fast Wiener filtering of CMB maps with Neural Networks
• The Simons Observatory: Project Overview

Cited by in corpus (1)

• Neural Networks for cosmological model selection and feature importance using Cosmic Microwave Background data