# Classifying the formation processes of S0 galaxies using Convolutional Neural Networks

## TL;DR

This paper demonstrates that convolutional neural networks can accurately classify simulated S0 galaxies based on their formation processes and predict merger mass ratios, linking morphological features to physical origins.

## Contribution

The study introduces a CNN-based method to classify galaxy formation pathways and predict merger mass ratios from simulated galaxy images, highlighting physical interpretability.

## Key findings

- CNNs classify S0 galaxy formation pathways with over 99% accuracy.
- Predicted merger mass ratios align within one standard deviation of true values.
- CNNs show potential for linking galaxy morphology to physical formation processes.

## Abstract

Numerous studies have demonstrated the ability of Convolutional Neural Networks (CNNs) to classify large numbers of galaxies in a manner which mimics the expertise of astronomers. Such classifications are not always physically motivated, however, such as categorising galaxies by their morphological types. In this work, we consider the use of CNNs to classify simulated S0 galaxies based on fundamental physical properties. In particular, we undertake two investigations: (1) the classification of simulated S0 galaxies into three distinct evolutionary paths (isolated, tidal interaction in a group halo, and Spiral-Spiral merger), and (2) the prediction of the mass ratio for the S0s formed via mergers. To train the CNNs, we first run several hundred N-body simulations to model the formation of S0s under idealised conditions; and then we build our training datasets by creating images of stellar density and two dimensional kinematic maps for each simulated S0. Our trained networks have remarkable accuracies exceeding 99% when classifying the S0 formation pathway. For the case of predicting merger mass ratios, the mean predictions are consistent with the true values to within roughly one standard deviation across the full range of our data. Our work demonstrates the potential of CNNs to classify galaxies by the fundamental physical properties which drive their evolution.