A catalog of visual-like morphologies in the 5 CANDELS fields using deep-learning

TL;DR

This paper introduces a deep-learning-based catalog of galaxy morphologies in five CANDELS fields, achieving high accuracy and low bias in classifying galaxy structures at a median redshift of 1.25.

Contribution

The study develops and applies a convolutional neural network to classify galaxy morphologies across multiple fields, surpassing traditional methods in accuracy and bias reduction.

Findings

ConvNets predict morphology probabilities with ~10% scatter.

Miss-classification rate is less than 1%.

Outperforms CAS-based methods at high redshift.

Abstract

We present a catalog of visual like H-band morphologies of $\sim50.000$ galaxies ($H_{f160w}<24.5$) in the 5 CANDELS fields (GOODS-N, GOODS-S, UDS, EGS and COSMOS). Morphologies are estimated with Convolutional Neural Networks (ConvNets). The median redshift of the sample is $<z>\sim1.25$. The algorithm is trained on GOODS-S for which visual classifications are publicly available and then applied to the other 4 fields. Following the CANDELS main morphology classification scheme, our model retrieves the probabilities for each galaxy of having a spheroid, a disk, presenting an irregularity, being compact or point source and being unclassifiable. ConvNets are able to predict the fractions of votes given a galaxy image with zero bias and $\sim10\%$ scatter. The fraction of miss-classifications is less than $1\%$. Our classification scheme represents a major improvement with respect to CAS (Concentration-Asymmetry-Smoothness)-based methods, which hit a $20-30\%$ contamination limit at high z. The catalog is released with the present paper via the $\href{http://rainbowx.fis.ucm.es/Rainbow_navigator_public}{Rainbow\,database}$