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 ($\rho_{\rm igm}$), 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 $\rho_{\rm igm}$ 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 $\rho_{\rm igm}$. 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, $\hat{\rho}_{\rm igm}$ where $0.0 \le \hat{\rho}_{\rm igm, n} < 10.0$, accurately with root mean squared error values ($\rm RMSE$) 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 ($v_{\rm rel}$) 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.