Abstract Details

Name: Arunima Banerjee
Affiliation: IISER Tirupati
Conference ID: ASI2021_506
Title : Dynamical parameters of interacting galaxies using CNN
Authors and Co-Authors : Prem Prakash (IISER Tirupati) Arunima Banerjee (IISER Tirupati) Pavan Kumar Perepu (IISER Tirupati)
Abstract Type :
Abstract Category : Extragalactic Astronomy
Abstract : Constructing dynamical models for interacting galaxies constrained by their observed structure and kinematics crucially depends on the correct choice of the values of their relative inclination ($i$) and viewing angle ($\theta$) (the angle between the line of sight and the normal to the plane of their orbital motion). We construct Deep Convolutional Neural Network (DCNN) models to determine the $i$ and $\theta$ of interacting galaxy pairs, using N-body $+$ Smoothed Particle Hydrodynamics (SPH) simulation data from the GALMER database for training. GalMer simulates only a discrete set of $i$ values ($0^{\circ}, 45^{\circ}, 75^{\circ} \text{ and } 90^{\circ}$) and almost all possible values of $\theta$ values in the range, $[-90, 90]$. Therefore, we have used classification for $i$ parameter and regression for $\theta$. In order to classify galaxy pairs based on their $i$ values only, we first construct DCNN models for (i) 2-class ($i$ = 0 $^{\circ}$, 45$^{\circ}$) (ii) 3-class ($i = 0^{\circ},45^{\circ}, 90^{\circ}$) classification, obtaining $F_1$ scores of 99\% and 98\% respectively. Further, for a classification based on both $i$ and $\theta$ values, we develop a DCNN model for a 9-class classification using different possible combinations of $i$ and $\theta$, and the $F_1$ score was 97$\%$. To estimate $\theta$ alone, we have used regression due to the availability of continuous values, and obtained a mean squared error value of 0.12. Finally, we also tested our DCNN model on real data from Sloan Digital Sky Survey. Our DCNN models could be extended to determine additional dynamical parameters, currently determined by trial and error method.