Neural network-based anomaly detection for high-resolution X-ray spectroscopy

Abstract

We propose an anomaly detection technique for high-resolution X-ray spectroscopy. The method is based on the neural network architecture variational autoencoder, and requires only {\it normal} samples for training. We implement the network using Python taking account of the effect of Poisson statistics carefully, and deonstrate the concept with simulated high-resolution X-ray spectral datasets of one-temperature, two-temperature and non-equilibrium plasma. Our proposed technique would assist scientists in finding important information that would otherwise be missed due to the unmanageable amount of data taken with future X-ray observatories.

Accepted for publication in MNRAS

References in corpus (22)

• Adam: A Method for Stochastic Optimization
• The Leiden/Argentine/Bonn (LAB) Survey of Galactic HI: Final data release of the combined LDS and IAR surveys with improved stray-radiation corrections
• Deep Learning for Anomaly Detection: A Survey
• Detection of An Unidentified Emission Line in the Stacked X-ray spectrum of Galaxy Clusters
• The Baryon Census in a Multiphase Intergalactic Medium: 30% of the Baryons May Still Be Missing
• The Quiescent Intracluster Medium in the Core of the Perseus Cluster
• Supernova remnants: the X-ray perspective
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• Fast Automated Analysis of Strong Gravitational Lenses with Convolutional Neural Networks
• Deep learning of multi-element abundances from high-resolution spectroscopic data
• Atmospheric gas dynamics in the Perseus cluster observed with Hitomi
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Atomic data and spectral modeling constraints from high-resolution X-ray observations of the Perseus cluster with Hitomi
• Hitomi constraints on the 3.5 keV line in the Perseus galaxy cluster
• Solar abundance ratios of the iron-peak elements in the Perseus Cluster
• Deep Convolutional Neural Networks as strong gravitational lens detectors
• Measurements of resonant scattering in the Perseus cluster core with Hitomi SXS
• Temperature Structure in the Perseus Cluster Core Observed with Hitomi
• The EBEX Balloon-Borne Experiment - Gondola, Attitude Control, and Control Software
• Projection effects in X-ray cores of cooling flow galaxy clusters
• EBIT Observation of Ar Dielectronic Recombination Lines Near the Unknown Faint X-Ray Feature Found in the Stacked Spectrum of Galaxy Clusters
• Neural network-based preprocessing to estimate the parameters of the X-ray emission of a single-temperature thermal plasma

Cited by in corpus (10)

• SILVERRUSH X: Machine Learning-Aided Selection of $9318$ LAEs at $z=2.2$, $3.3$, $4.9$, $5.7$, $6.6$, and $7.0$ from the HSC SSP and CHORUS Survey Data
• Searching for Anomalies in the ZTF Catalog of Periodic Variable Stars
• X-ray Study of Spatial Structures in Tycho's Supernova Remnant Using Unsupervised Deep Learning
• Accelerating the search for Axion-Like Particles with machine learning
• Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey
• Multiwavelength classification of X-ray selected galaxy cluster candidates using convolutional neural networks
• EmulART: Emulating Radiative Transfer -- A pilot study on autoencoder based dimensionality reduction for radiative transfer models
• Interpreting anomaly detection of SDSS spectra
• Application of deep learning to the evaluation of goodness in the waveform processing of transition-edge sensor calorimeters
• Identifying Anomalous DESI Galaxy Spectra with a Variational Autoencoder