A new way to constrain the densities of intra-group medium in groups of galaxies with convolutional neural networks

Abstract

Ram pressure (RP) can influence the evolution of cold gas content and star formation rates of galaxies. One of the key parameters for the strength of RP is the density of intra-group medium (${\rho }_{\mathrm{igm}}$), which is difficult to estimate if the X-ray emission from it is too weak to be observed. We propose a new way to constrain ${\rho }_{\mathrm{igm}}$ through an application of convolutional neural networks (CNNs) to simulated gas density and kinematic maps galaxies under strong RP. We train CNNs using $9\times 10^4$ 2D images of galaxies under various RP conditions, then validate performance with $10^4$ new test images. This new method can be applied to real observational data from ongoing WALLABY and SKA surveys to quickly obtain estimates of ${\rho }_{\mathrm{igm}}$. Simulated galaxy images have $1.0$ kpc resolution, which is consistent with that expected from the future WALLABY survey. The trained CNN models predict the normalised IGM density, ${\hat{\rho }}_{\mathrm{igm}}$ where $0.0\le {\hat{\rho }}_{\mathrm{igm},\mathrm{n}}<10.0$, accurately with root mean squared error values ($\mathrm{RMSE}$) of $0.72$, $0.83$ and $0.74$ for the density, kinematic and joined 2D maps, respectively. Trained models are unable to predict the relative velocity of galaxies with respect to the IGM ($v_{\mathrm{rel}}$) precisely, and struggle to generalise for different RP conditions. We apply our CNNs to the observed HI column density map of NGC 1566 in the Dorado group to estimate its IGM density.

arXiv comment15 pages, 12 figures

References in corpus (40)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• The Structure of Cold Dark Matter Halos
• Improving neural networks by preventing co-adaptation of feature detectors
• Star Formation in Galaxies Along the Hubble Sequence
• YOLOv3: An Incremental Improvement
• ADADELTA: An Adaptive Learning Rate Method
• Environmental Effects on Late-Type Galaxies in Nearby Clusters
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Origin of Star Formation Gradients in Rich Galaxy Clusters
• Ram Pressure Stripping of Spiral Galaxies in Clusters
• Simultaneous ram pressure and tidal stripping; how dwarf spheroidals lost their gas
• VLA HI Observations of Gas Stripping in the Virgo Cluster Spiral NGC 4522
• Strangulation in Galaxy Groups
• WALLABY -- An SKA Pathfinder HI Survey
• Gas Stripping of Dwarf Galaxies in Clusters of Galaxies
• Effects of Ram-Pressure from Intracluster Medium on the Star Formation Rate of Disk Galaxies in Clusters of Galaxies
• The GALEX view of the Herschel Reference Survey - Ultraviolet structural properties of nearby galaxies
• Classifying Radio Galaxies with Convolutional Neural Network
• Galactic star formation enhanced and quenched by ram pressure in groups and clusters
• Non-Gaussian information from weak lensing data via deep learning
• A History of HI Stripping in Virgo: A Phase-space View of VIVA Galaxies
• Deep learning from 21-cm tomography of the Cosmic Dawn and Reionization
• Emulation of reionization simulations for Bayesian inference of astrophysics parameters using neural networks
• Gas and dark matter in the Sculptor group: NGC 300
• A Deep Learning Approach to Galaxy Cluster X-ray Masses
• Deep learning for galaxy surface brightness profile fitting
• Dust-regulated galaxy formation and evolution:A new chemodynamical model with live dust particles
• Constraining the astrophysics and cosmology from 21cm tomography using deep learning with the SKA
• Halpha3: an Halpha imaging survey of HI selected galaxies from ALFALFA. IV. Structure of galaxies in the Local and Coma Superclusters
• MHD simulations of ram pressure stripping of a disk galaxy
• The Journey Counts: The Importance of Including Orbits when Simulating Ram Pressure Stripping
• Stellar populations in gas-rich galaxy mergers I. Dependence on star formation history
• How convolutional neural network see the world - A survey of convolutional neural network visualization methods
• WALLABY Early Science - III. An HI Study of the Spiral Galaxy NGC 1566
• Satellite dwarf galaxies: Stripped but not quenched
• The effects of ram-pressure stripping on the internal kinematics of simulated spiral galaxies
• CASI: A Convolutional Neural Network Approach for Shell Identification
• Ram Pressure Stripping in the Low Luminosity Virgo Cluster Elliptical Galaxy NGC 4476
• Explaining the enhanced star formation rate of Jellyfish galaxies in galaxy clusters
• Classifying the formation processes of S0 galaxies using Convolutional Neural Networks

Cited by in corpus (3)

• Morphological classification of galaxies with deep learning: comparing 3-way and 4-way CNNs
• Quantifying the fine structures of disk galaxies with deep learning:Segmentation of spiral arms in different Hubble types
• A self-supervised, physics-aware, Bayesian neural network architecture for modelling galaxy emission-line kinematics