X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning

Abstract

Recent rapid development of deep learning algorithms, which can implicitly capture structures in high-dimensional data, opens a new chapter in astronomical data analysis. We report here a new implementation of deep learning techniques for X-ray analysis. We apply a variational autoencoder (VAE) using a deep neural network for spatio-spectral analysis of data obtained by Chandra X-ray Observatory from Tycho's supernova remnant (SNR). We established an unsupervised learning method combining the VAE and a Gaussian mixture model (GMM), where the dimensions of the observed spectral data are reduced by the VAE, and clustering in feature space is performed by the GMM. We found that some characteristic spatial structures, such as the iron knot on the eastern rim, can be automatically recognised by this method, which uses only spectral properties. This result shows that unsupervised machine learning can be useful for extracting characteristic spatial structures from spectral information in observational data (without detailed spectral analysis), which would reduce human-intensive preprocessing costs for understanding fine structures in diffuse astronomical objects, e.g., SNRs or clusters of galaxies. Such data-driven analysis can be used to select regions from which to extract spectra for detailed analysis and help us make the best use of the large amount of spectral data available currently and arriving in the coming decades.

arXiv comment11 pages, 12 figures, 3 tables, accepted for publication in MNRAS

References in corpus (31)

• Scikit-learn: Machine Learning in Python
• On the Absorption of X-rays in the Interstellar Medium
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• SmoothGrad: removing noise by adding noise
• Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• Cosmic Ray Acceleration at the Forward Shock in Tycho's Supernova Remnant: Evidence from Chandra X-ray Observations
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Tycho Brahe's 1572 supernova as a standard type Ia explosion revealed from its light echo spectrum
• Wasserstein Auto-Encoders
• The blast wave of Tycho's supernova remnant
• XMM-Newton observation of the Tycho Supernova Remnant
• Deep Recurrent Neural Networks for Supernovae Classification
• Expansion Velocity of Ejecta in Tycho's Supernova Remnant Measured by Doppler Broadened X-ray Line Emission
• X-Ray Measured Dynamics of Tycho's Supernova Remnant
• Evidence For Particle Acceleration to the Knee of the Cosmic Ray Spectrum in Tycho's Supernova Remnant
• X-Ray Emission Line Imaging and Spectroscopy of Tycho's Supernova Remnant
• Application of Deep Learning methods to analysis of Imaging Atmospheric Cherenkov Telescopes data
• New Evidence for Efficient Collisionless Heating of Electrons at the Reverse Shock of a Young Supernova Remnant
• The X-ray Iron Emission from Tycho's Supernova Remnant
• X-ray Emission from Strongly Asymmetric Circumstellar Material in the Remnant of Kepler's Supernova
• Suzaku Observations of Tycho's Supernova Remnant
• The Origin of the Iron-Rich Knot in Tycho's Supernova Remnant
• Direct Ejecta Velocity Measurements of Tycho's Supernova Remnant
• Neural network-based anomaly detection for high-resolution X-ray spectroscopy
• Single-epoch supernova classification with deep convolutional neural networks
• Principal Component Analysis and Radiative Transfer modelling of Spitzer IRS Spectra of Ultra Luminous Infrared Galaxies
• Parametric modelling of the 3.6um to 8um colour distributions of galaxies in the SWIRE Survey
• Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma
• Reverse-Shock in Tycho's Supernova Remnant
• Machine-learning identification of extragalactic objects in the optical-infrared all-sky surveys

Cited by in corpus (10)

• Dimensionality Reduction of SDSS Spectra with Variational Autoencoders
• A review of unsupervised learning in astronomy
• Data mining techniques on astronomical spectra data. I : Clustering Analysis
• Machine Learning Approach to Integral Field Unit Spectroscopy Observations: I. HII Region Kinematics
• Stellar Spectral Interpolation using Machine Learning
• A fresh perspective on the 3D dynamics of Tycho's supernova remnant: Ejecta asymmetries in the X-ray band
• KilonovAE: Exploring Kilonova Spectral Features with Autoencoders
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• Spatio-temporal characterization of Cassiopeia A
• Sifting the debris: Patterns in the SNR population with unsupervised ML methods