A Machine Learning Approach to Enhancing eROSITA Observations

Abstract

The eROSITA X-ray telescope, launched in 2019, is predicted to observe roughly 100,000 galaxy clusters. Follow-up observations of these clusters from Chandra, for example, will be needed to resolve outstanding questions about galaxy cluster physics. Deep Chandra cluster observations are expensive and follow-up of every eROSITA cluster is infeasible, therefore, objects chosen for follow-up must be chosen with care. To address this, we have developed an algorithm for predicting longer duration, background-free observations based on mock eROSITA observations. We make use of the hydrodynamic cosmological simulation Magneticum, have simulated eROSITA instrument conditions using SIXTE, and have applied a novel convolutional neural network to output a deep Chandra-like "super observation" of each cluster in our simulation sample. Any follow-up merit assessment tool should be designed with a specific use case in mind; our model produces observations that accurately and precisely reproduce the cluster morphology, which is a critical ingredient for determining cluster dynamical state and core type. Our model will advance our understanding of galaxy clusters by improving follow-up selection and demonstrates that image-to-image deep learning algorithms are a viable method for simulating realistic follow-up observations.

arXiv comment21 pages, 11 figures, 3 tables. Minor changes upon revision. Corrected caption of Figure 3. Added discussion of alternative asymmetry metrics. To be published in the Astrophysical Journal

References in corpus (55)

• Astropy: A Community Python Package for Astronomy
• Seven-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Cosmological Interpretation
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• A direct empirical proof of the existence of dark matter
• Toward a halo mass function for precision cosmology: the limits of universality
• Cosmological Parameters from Observations of Galaxy Clusters
• Formation of Galaxy Clusters
• A New Non-Parametric Approach to Galaxy Morphological Classification
• Mechanical Feedback from Active Galactic Nuclei in Galaxies, Groups, and Clusters
• Testing X-ray Measurements of Galaxy Clusters with Cosmological Simulations
• A New Robust Low-Scatter X-ray Mass Indicator for Clusters of Galaxies
• Cosmological simulations of black hole growth: AGN luminosities and downsizing
• Rotation-Dependent Catastrophic Disruption of Gravitational Aggregates
• Residual Gas Motions in the Intracluster Medium and Bias in Hydrostatic Measurements of Mass Profiles of Clusters
• Dependence of the outer density profiles of halos on their mass accretion rate
• The galaxy cluster mass scale and its impact on cosmological constraints from the cluster population
• Halo mass function: Baryon impact, fitting formulae and implications for cluster cosmology
• On the nature of hydrostatic equilibrium in galaxy clusters
• Searching for Cool Core Clusters at High redshift
• Cool Core Clusters from Cosmological Simulations
• SZ effects in the Magneticum Pathfinder Simulation: Comparison with the Planck, SPT, and ACT results
• Gas Clumping in the Outskirts of Lambda-CDM Clusters
• Using transfer learning to detect galaxy mergers
• Weighing Galaxy Clusters with Gas. II. On the Origin of Hydrostatic Mass Bias in LambdaCDM Galaxy Clusters
• X-Ray morphological analysis of the Planck ESZ clusters
• Investigating the velocity structure and X-ray observable properties of simulated galaxy clusters with PHOX
• Cosmology and Astrophysics from Relaxed Galaxy Clusters I: Sample Selection
• SIXTE -- The Generic X-ray Instrument Simulation Toolkit
• Fast cosmic web simulations with generative adversarial networks
• Transfer learning for galaxy morphology from one survey to another
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Analytical model for non-thermal pressure in galaxy clusters - III. Removing the hydrostatic mass bias
• A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
• ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks
• Weighing Galaxy Clusters with Gas. I. On the Methods of Computing Hydrostatic Mass Bias
• A Morphology--Cosmology Connection for X--Ray Clusters
• Shapes of Gas, Gravitational Potential and Dark Matter in Lambda-CDM Clusters
• Constraints on dark matter self-interaction from the internal density profiles of X-COP galaxy clusters
• Morphology parameters: substructure identification in X-ray galaxy clusters
• Learning to Denoise Astronomical Images with U-nets
• AGN contamination of galaxy-cluster thermal X-ray emission: predictions for eRosita from cosmological simulations
• Observing simulated galaxy clusters with PHOX: a novel X-ray photon simulator
• Forecasts on dark energy from the X-ray cluster survey with eROSITA: constraints from counts and clustering
• Characterizing hydrostatic mass bias with Mock-X
• Correlations between Triaxial Shapes and Formation History of Dark Matter Haloes
• Imprints of Mass Accretion History on the Shape of the Intracluster Medium and the $T_X-M$ Relation
• The eROSITA Final Equatorial-Depth Survey (eFEDS): Characterization of Morphological Properties of Galaxy Groups and Clusters
• Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
• Constraining Cluster Physics with the Shape of X-ray Clusters: Comparison of Local X-ray Clusters versus LCDM Clusters
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• SHAPing the Gas: Understanding Gas Shapes in Dark Matter Haloes with Interpretable Machine Learning
• Recent Dynamical Relaxation of Galaxy Clusters: Evidence for a Low-${\Omega }_m$ Universe
• Multiband galaxy morphologies for CLASH: a convolutional neural network transferred from CANDELS
• Emulating Sunyaev-Zeldovich Images of Galaxy Clusters using Auto-Encoders
• Origin of cool cores, cold fronts and spiral structures in cool core clusters of galaxies

Cited by in corpus (2)

• Benchmarks and Explanations for Deep Learning Estimates of X-ray Galaxy Cluster Masses
• Painting baryons onto N-body simulations of galaxy clusters with image-to-image deep learning