CEERS Key Paper. IX. Identifying Galaxy Mergers in CEERS NIRCam Images Using Random Forests and Convolutional Neural Networks

TL;DR

This paper develops machine learning models using random forests and CNNs to identify galaxy mergers in high-redshift JWST CEERS images, achieving moderate success and analyzing model features and merger rates.

Contribution

It introduces trained ML models on simulated data for galaxy merger identification in JWST images, assessing their performance on real observations.

Findings

Models correctly classify 60-70% of simulated mergers

Performance drops to 40-60% on real data at certain redshifts

CNNs tend to overclassify mergers, while random forests have variable accuracy

Abstract

A crucial yet challenging task in galaxy evolution studies is the identification of distant merging galaxies, a task which suffers from a variety of issues ranging from telescope sensitivities and limitations to the inherently chaotic morphologies of young galaxies. In this paper, we use random forests and convolutional neural networks to identify high-redshift JWST CEERS galaxy mergers. We train these algorithms on simulated $3<z<5$ CEERS galaxies created from the IllustrisTNG subhalo morphologies and the Santa Cruz SAM lightcone. We apply our models to observed CEERS galaxies at $3<z<5$. We find that our models correctly classify $\sim60-70\%$ of simulated merging and non-merging galaxies; better performance on the merger class comes at the expense of misclassifying more non-mergers. We could achieve more accurate classifications, as well as test for the dependency on physical parameters such as gas fraction, mass ratio, and relative orbits, by curating larger training sets. When applied to real CEERS galaxies using visual classifications as ground truth, the random forests correctly classified $40-60\%$ of mergers and non-mergers at $3<z<4$, but tended to classify most objects as non-mergers at $4<z<5$ (misclassifying $\sim70\%$ of visually-classified mergers). On the other hand, the CNNs tended to classify most objects as mergers across all redshifts (misclassifying $80-90\%$ of visually-classified non-mergers). We investigate what features the models find most useful, as well as characteristics of false positives and false negatives, and also calculate merger rates derived from the identifications made by the models.