paper

Classifying merger stages with adaptive deep learning and cosmological hydrodynamical simulations

arXiv:2502.06254 · doi:10.1051/0004-6361/202452659

Abstract

Hierarchical merging of galaxies plays an important role in galaxy formation and evolution. Mergers could trigger key evolutionary phases such as starburst activities and active accretion periods onto supermassive black holes at the centres of galaxies. We aim to detect mergers and merger stages (pre- and post-mergers) across cosmic history and test whether it is better to detect mergers and their merger stages simultaneously or hierarchically. In addition, we want to test the impact of merger time relative to the coalescence of merging galaxies. First, we generated realistic mock JWST images of simulated galaxies selected from the IllustrisTNG cosmological hydrodynamical simulations. Then we trained deep learning (DL) models in the Zoobot Python package to classify galaxies into merging/non-merging galaxies and their merger stages. We used two different set-ups: (i) two-stage, in which we classify galaxies into mergers and non-mergers and then classify the mergers into pre-mergers and post-mergers, and (ii) one-stage, in which merger/non-merger and merger stages are classified simultaneously. We found that the one-stage classification set-up moderately outperforms the two-stage set-up, offering better overall accuracy and precision, particularly for the non-merger class. Pre-mergers can be classified with the highest precision in both set-ups, possibly due to the more recognisable merging features and the presence of merging companions. The image signal-to-noise ratio affects the performance of the DL classifiers, but not much after a certain threshold is crossed. Both precision and recall of the classifiers depend strongly on merger time, finding it more difficult to identify true mergers observed at stages that are more distant to coalescence. For pre-mergers, we recommend selecting mergers which will merge in the next 0.4 Gyrs, to achieve a good balance between precision and recall.

References in corpus (20)