Evaluating the feasibility of interpretable machine learning for globular cluster detection
arXiv:2204.00017 · doi:10.1051/0004-6361/202243354
Abstract
Extragalactic globular clusters (GCs) are important tracers of galaxy formation and evolution. Obtaining GC catalogues from photometric data involves several steps which will likely become too time-consuming to perform on the large data volumes that are expected from upcoming wide-field imaging projects such as Euclid. In this work, we explore the feasibility of various machine learning (ML) methods to aid the search for GCs. We use archival Hubble Space Telescope data in the F475W and F850LP bands of 141 early-type galaxies in the Fornax and Virgo galaxy clusters. Using existing GC catalogues to label the data, we obtain an extensive data set of 84929 sources containing 18556 GCs and we train several ML methods both on image and tabular data containing physically relevant features extracted from the images. We find that our evaluated ML models are capable of producing catalogues of similar quality as the existing ones. The best performing methods, ensemble-based models like random forests and convolutional neural networks, recover ~ 90-94 % of GCs while producing an acceptable amount of false detections (~ 6-8 %) - with some falsely detected sources being identifiable as GCs that have not been labelled as such in the used catalogues. In the magnitude range 22 < m4_g < 24.5 mag, 98 - 99 % of GCs are recovered. We even find such high performance levels when training on Virgo and evaluating on Fornax data (and vice versa), illustrating that the models are transferable to environments with different conditions such as different distances than in the used training data. Additionally, we demonstrate how interpretable methods can be used to better understand model predictions, recovering that magnitudes, colours, and sizes are important for identifying GCs. These are encouraging results, indicating that similar methods can be applied for creating GC catalogues for a large number of galaxies.
accepted for publication in A&A, 13 pages, 10 figures (excluding appendix). Abstract abridged for arXiv
References in corpus (18)
- Array Programming with NumPy
- Wide-Field InfrarRed Survey Telescope-Astrophysics Focused Telescope Assets WFIRST-AFTA 2015 Report
- The ACS Virgo Cluster Survey. XII. The Luminosity Function of Globular Clusters in Early Type Galaxies
- The ACS Fornax Cluster Survey. I. Introduction to the Survey and Data Reduction Procedures
- Galactic Dark Matter Halos and Globular Cluster Populations. III: Extension to Extreme Environments
- The Fornax 3D project: unveiling the thick disk origin in FCC 170: signs of accretion?
- Using H-alpha Morphology and Surface Brightness Fluctuations to Age-Date Star Clusters in M83
- Star cluster formation in the most extreme environments: Insights from the HiPEEC survey
- Globular Cluster Systems in Brightest Cluster Galaxies. III: Beyond Bimodality
- Star Cluster Classification in the PHANGS-HST Survey: Comparison between Human and Machine Learning Approaches
- The Fornax Deep Survey with VST. IX. The catalog of sources in the FDS area, with an example study for globular clusters and background galaxies
- Tidal origin of NGC 1427A in the Fornax cluster
- Luminosity functions of globular clusters in five nearby spiral galaxies using HST/ACS images
- StarcNet: Machine Learning for Star Cluster Identification
- Scaling relations for globular cluster systems in early-type galaxies. II. Is there an environmental dependence?
- Dwarfs from the Dark (Energy Survey): a machine learning approach to classify dwarf galaxies from multi-band images
- Robustness of deep learning algorithms in astronomy -- galaxy morphology studies
- Detection of extragalactic Ultra-Compact Dwarfs and Globular Clusters using Explainable AI techniques