PAH Marks the Spot: Digging for Buried Clusters in Nearby Star-forming Galaxies

TL;DR

Embedded-phase star clusters in nearby galaxies are obscured by dust, limiting optical SED analyses. The study combines near- and mid-infrared JWST imaging with HST UV/optical data to identify embedded clusters via a by-eye search and then trains convolutional neural networks in a deep transfer learning framework on the identified sample. The approach yields 292 embedded cluster candidates with a median age of $4.5$ Myr and a mean line-of-sight extinction of $\left< A_V \right> = 6.0$ mag, with a median stellar mass of $10^3\,M_\odot$, and evaluates eight ML configurations through confusion matrices to optimize the transfer-learning pipeline. Optimized ML methods could enable scalable future catalogs of embedded clusters beyond the 11-galaxy PHANGS-JWST sample, advancing our understanding of early cluster evolution and feedback in nearby galaxies.

Abstract

The joint capabilities of the Hubble Space Telescope (HST) and JWST allow for an unparalleled look at the early lives of star clusters at near- and mid-infrared wavelengths. We present here a multiband analysis of embedded young stellar clusters in 11 nearby, star-forming galaxies, using the PHANGS-JWST and PHANGS-HST datasets. We use the Zooniverse citizen science platform to conduct an initial by-eye search for embedded clusters in near-UV/optical/near-infrared images that trace stellar continuum emission, the Paschen$α$ and H$α$ recombination lines, and the 3.3 $μ$m polycyclic aromatic hydrocarbon feature and its underlying continuum. With this approach, we identify 292 embedded cluster candidates for which we characterize their ages, masses, and levels of line-of-sight extinction by comparing the photometric data to predictions from stellar population models. The embedded cluster candidates have a median age of 4.5 Myr and an average line-of-sight extinction $\left< A_V \right> = 6.0$ mag. We determine lower limits on source stellar masses, resulting in a median stellar mass of $10^3$ $M_{\odot}$. We use this sample of embedded cluster candidates to train multiple convolutional neural network models to carry out deep transfer learning-based searches for embedded clusters. With the aim of optimizing models for future catalog production, we compare results for four variations of training data using two neural networks. Confusion matrices for all eight model configurations, as well as inter-model identification trends, are presented. With refinement of the training sample, we determine that optimized models could serve as a pathway for future embedded cluster identification beyond our 11 galaxy sample.