Deriving star cluster parameters with convolutional neural networks. I. Age, mass, and size

Abstract

Context. Convolutional neural networks (CNNs) have been proven to perform fast classification and detection on natural images and have potential to infer astrophysical parameters on the exponentially increasing amount of sky survey imaging data. The inference pipeline can be trained either from real human-annotated data or simulated mock observations. Until now star cluster analysis was based on integral or individual resolved stellar photometry. This limits the amount of information that can be extracted from cluster images. Aims. Develop a CNN-based algorithm aimed to simultaneously derive ages, masses, and sizes of star clusters directly from multi-band images. Demonstrate CNN capabilities on low mass semi-resolved star clusters in a low signal-to-noise ratio regime. Methods. A CNN was constructed based on the deep residual network (ResNet) architecture and trained on simulated images of star clusters with various ages, masses, and sizes. To provide realistic backgrounds, M31 star fields taken from the PHAT survey were added to the mock cluster images. Results. The proposed CNN was verified on mock images of artificial clusters and has demonstrated high precision and no significant bias for clusters of ages $\lesssim$3Gyr and masses between 250 and 4,000 ${\mathrm{M}}_{\odot }$. The pipeline is end-to-end, starting from input images all the way to the inferred parameters; no hand-coded steps have to be performed: estimates of parameters are provided by the neural network in one inferential step from raw images.

arXiv comment11 pages, 12 figures

References in corpus (28)

• Adam: A Method for Stochastic Optimization
• On the variation of the Initial Mass Function
• Improving neural networks by preventing co-adaptation of feature detectors
• PARSEC: stellar tracks and isochrones with the PAdova and TRieste Stellar Evolution Code
• Binary companions of evolved stars in APOGEE DR14: Search method and catalog of ~5,000 companions
• Deep Learning using Rectified Linear Units (ReLU)
• Gaia Data Release 1. Summary of the astrometric, photometric, and survey properties
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Improving galaxy morphologies for SDSS with Deep Learning
• The Panchromatic Hubble Andromeda Treasury
• Identifying Exoplanets with Deep Learning: A Five Planet Resonant Chain around Kepler-80 and an Eighth Planet around Kepler-90
• CMU DeepLens: Deep Learning For Automatic Image-based Galaxy-Galaxy Strong Lens Finding
• Finding Strong Gravitational Lenses in the Kilo Degree Survey with Convolutional Neural Networks
• Star Clusters in M31: I. A Catalog and a Study of the Young Clusters
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Panchromatic Hubble Andromeda Treasury XVIII. The High-mass Truncation of the Star Cluster Mass Function
• Deep Learning Identifies High-z Galaxies in a Central Blue Nugget Phase in a Characteristic Mass Range
• PHAT Stellar Cluster Survey I. Year 1 Catalog and Integrated Photometry
• PHAT Stellar Cluster Survey. II. Andromeda Project Cluster Catalog
• LensExtractor: A Convolutional Neural Network in Search of Strong Gravitational Lenses
• The Panchromatic Hubble Andromeda Treasury V: Ages and Masses of the Year 1 Stellar Clusters
• Fast Point Spread Function Modeling with Deep Learning
• Effective Image Differencing with ConvNets for Real-time Transient Hunting
• Deriving physical parameters of unresolved star clusters. I. Age, mass, and extinction degeneracies
• Compact Star Clusters in the M31 Disk
• Deriving physical parameters of unresolved star clusters. II. The degeneracies of age, mass, extinction, and metallicity
• Deriving physical parameters of unresolved star clusters III. Application to M31 PHAT clusters
• Deriving structural parameters of semi-resolved star clusters. FitClust: a program for crowded fields

Cited by in corpus (14)

• Star Cluster Classification in the PHANGS-HST Survey: Comparison between Human and Machine Learning Approaches
• PHANGS-HST: New Methods for Star Cluster Identification in Nearby Galaxies
• Estimating ages and metallicities of M31 star clusters from LAMOST DR6
• Study of star clusters in the M83 galaxy with a convolutional neural network
• Evaluating the feasibility of interpretable machine learning for globular cluster detection
• Identification of new M31 star cluster candidates from PAndAS images using convolutional neural networks
• Characterising lognormal fractional-Brownian-motion density fields with a Convolutional Neural Network
• Deriving physical parameters of unresolved star clusters. VII. Adaptive aperture photometry of the M31 PHAT star clusters
• Deriving star cluster parameters with convolutional neural networks. II. Extinction and cluster/background classification
• 200,000+ Deep Learning-inferred Periods of Stellar Variability from the All-Sky Automated Survey for Supernovae
• Predicting Images for the Dynamics Of stellar Clusters (π-DOC): a deep learning framework to predict mass, distance and age of globular clusters
• Deriving physical parameters of unresolved star clusters. VIII. Limits of aperture photometry for star cluster studies
• Sparse logistic regression for RR Lyrae vs binaries classification
• Deriving physical parameters of unresolved star clusters. IX. Sky background effects in the aperture photometry