Galaxy mergers classification using CNNs trained on S\'ersic models, residuals and raw images

TL;DR

This study evaluates the effectiveness of CNNs trained on different galaxy image components—original, Sersic model, and residual images—for classifying galaxy mergers, revealing that both faint features and positional data contribute to accurate detection.

Contribution

It introduces a comprehensive analysis of the relative importance of morphological features in CNN-based galaxy merger classification using simulated data.

Findings

CNN on full images achieves 74% accuracy.

Residual images alone yield 68% accuracy.

Position and shape information are both crucial for classification.

Abstract

Galaxy mergers are crucial for understanding galaxy evolution, and with large upcoming datasets, automated methods such as Convolutional Neural Networks (CNNs) are essential for efficient detection. It is understood that CNNs classify mergers by identifying deviations from the regular, expected shapes of galaxies, particularly faint features that are indicative of a merger event. In this work, we present a novel investigation of the relative importance of different morphological components, namely faint residual features and position and spatial structure, in CNN-based binary classification of galaxies into merger and non-merger classes. Using mock images from the IllustrisTNG simulations processed to mimic Hyper Suprime-Cam (HSC) observations, we fit S\'ersic profiles to each galaxy and generate three datasets: original images, model images containing only smooth S\'ersic profiles, and residual images highlighting faint features after model subtraction. We train three identical CNNs on these datasets: CNN1 on original images, CNN2 on model images, and CNN3 on residual images. CNN1, trained on full images, achieves the highest accuracy of 74 percent. CNN2, using only shape information including source position, achieves 70 percent, while CNN3, using only faint residual features, achieves 68 percent. We find that galaxy merger classification is possible using either faint features or the position and S\'ersic profile information present in residual and model images, respectively. Our results demonstrate that not only faint features but also source position information play complementary roles in merger classification. This has important implications for the design and interpretation of machine learning methods for galaxy morphology, particularly in regimes where specific image components may be enhanced or suppressed.