Estimating dynamical parameters of two interacting galaxies using deep learning

ABSTRACT The science behind Galaxy interaction and mergers has a fundamental role gives us an insight into galaxy formation its evolution. Fluctuating angular momentum is responsible for extraordinary events like polar rings, tidal tails, ripples. Various parameters the mass ratio of interacting galaxy, orbital parameters, distribution, morphologies are required to study different phenomena related interactions. Convolutional neural networks (CNN) widely used predict image data. Thus, we CNN as our approach problem. In this work, will use data from state-of-the-art magnetohydrodynamic simulations GalMer database at dynamical using snapshots merging pairs galaxies feeding them Deep Learning model. aiming would be spin, relative inclination (i), viewing angle (θ), azimuthal (ϕ). We aim download bulk web scraping method. Here model can continuous exact values parameters. have achieved 0.9986 R-squared value mean absolute error 0.4348 on testing end, Sloan Digital Sky Survey test trained some real images.