Performance of morphological classifiers for galaxy mergers compared to current machine learning methods
Abstract
Aims. Non-parametric morphological statistics can be used for efficient classification of galaxy mergers. This work aims to compare the performance of morphological merger classifiers to state-of-the-art machine learning (ML) models. A secondary aim is to produce updated criteria for mergers based on non-parametric morphological statistics. Methods. The Gini coefficient (G), M20 statistic, and concentration (C) were calculated for mock Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) images based on the IllustrisTNG and Horizon-AGN simulations, and observations from HSC-SSP. The IllustrisTNG images were used to find the line which best separates mergers and non-mergers in 2D morphological space with a Markov Chain Monte-Carlo (MCMC) method. Results. Based on the MCMC results, we classified galaxies with G>(−0.267±0.081)M20+(0.143±0.012) or G>(0.162±0.048)C−(0.149±0.12) as mergers, these criteria had precisions of 69.5\% and 72.3\% respectively when applied to previously unseen IllustrisTNG mock HSC-SSP images. The precisions of the morphological classifications are consistent with state-of-the-art ML methods. The morphological classifiers were found to be effective at selecting only pre-mergers; post-merger galaxies are indistinguishable from non-mergers in terms of their G, M20, and C values. Morphological classifiers displayed a similar robustness to new data to ML methods up to a redshift of ∼0.52 and maintained robustness better than ML methods based on convolutional neural networks in the redshift range 0.52<z<1. Conclusions. This work presents updated morphological classifiers which achieve similar precisions to ML based merger classifiers with a high robustness to new data. New morphological statistics are needed to identify the features of post-merger galaxies.
Related
- A probabilistic approach to separate mergers and jellyfish galaxies: Application of morphological non-parametric indexes to the DESI Legacy Survey
- Deep learning from the crowd Fundamentals of morphological galaxy classification
- Aligned Hierarchical Black Hole Mergers in Active-Galactic-Nuclei Disks Revealed by GWTC-4
- Ballistic mixing: Stellar mergers drive internal mixing in extremely massive stars with implications for proto-globular cluster pollution
- Effect of galaxy mergers on dust masses
BibTeX
@misc{cotter2026performance,
title = {{Performance of morphological classifiers for galaxy mergers compared to current machine learning methods}},
author = {Aidan P. Cotter and William J. Pearson and Subhrata Dey and Berta Margalef-Bentabol and Alejandro Guzmán-Ortega and Vicente Rodriguez-Gomez},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.09209},
eprint = {2607.09209},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.09209},
}
RIS
TY - UNPB
TI - Performance of morphological classifiers for galaxy mergers compared to current machine learning methods
AU - Aidan P. Cotter
AU - William J. Pearson
AU - Subhrata Dey
AU - Berta Margalef-Bentabol
AU - Alejandro Guzmán-Ortega
AU - Vicente Rodriguez-Gomez
PY - 2026
DA - 2026/09/18
PB - arXiv
DO - 10.48550/arxiv.2607.09209
UR - https://arxiv.org/abs/2607.09209
AB - Aims. Non-parametric morphological statistics can be used for efficient classification of galaxy mergers. This work aims to compare the performance of morphological merger classifiers to state-of-the-art machine learning (ML) models. A secondary aim is to produce updated criteria for mergers based on non-parametric morphological statistics. Methods. The Gini coefficient (G), M_20 statistic, and concentration (C) were calculated for mock Hyper Suprime-Cam Subaru Strategic Program (HSC-SSP) images based on the IllustrisTNG and Horizon-AGN simulations, and observations from HSC-SSP. The IllustrisTNG images were used to find the line which best separates mergers and non-mergers in 2D morphological space with a Markov Chain Monte-Carlo (MCMC) method. Results. Based on the MCMC results, we classified galaxies with G>(−0.267±0.081)M_20+(0.143±0.012) or G>(0.162±0.048)C−(0.149±0.12) as mergers, these criteria had precisions of 69.5\% and 72.3\% respectively when applied to previously unseen IllustrisTNG mock HSC-SSP images. The precisions of the morphological classifications are consistent with state-of-the-art ML methods. The morphological classifiers were found to be effective at selecting only pre-mergers; post-merger galaxies are indistinguishable from non-mergers in terms of their G, M_20, and C values. Morphological classifiers displayed a similar robustness to new data to ML methods up to a redshift of ∼0.52 and maintained robustness better than ML methods based on convolutional neural networks in the redshift range 0.52<z<1. Conclusions. This work presents updated morphological classifiers which achieve similar precisions to ML based merger classifiers with a high robustness to new data. New morphological statistics are needed to identify the features of post-merger galaxies.
ER -