GalaxiesML: a dataset of galaxy images, photometry, redshifts, and structural parameters for machine learning

TL;DR

The aim of GalaxiesML is to provide a robust dataset that can be used not only for astrophysics but also for machine learning, where image properties cannot be validated by the human eye and are instead governed by physical laws.

Abstract

We present a dataset built for machine learning applications consisting of galaxy photometry, images, spectroscopic redshifts, and structural properties. This dataset comprises 286,401 galaxy images and photometry from the Hyper-Suprime-Cam Survey PDR2 in five imaging filters ($g,r,i,z,y$) with spectroscopically confirmed redshifts as ground truth. Such a dataset is important for machine learning applications because it is uniform, consistent, and has minimal outliers but still contains a realistic range of signal-to-noise ratios. We make this dataset public to help spur development of machine learning methods for the next generation of surveys such as Euclid and LSST. The aim of GalaxiesML is to provide a robust dataset that can be used not only for astrophysics but also for machine learning, where image properties cannot be validated by the human eye and are instead governed by physical laws. We describe the challenges associated with putting together a dataset from publicly available archives, including outlier rejection, duplication, establishing ground truths, and sample selection. This is one of the largest public machine learning-ready training sets of its kind with redshifts ranging from 0.01 to 4. The redshift distribution of this sample peaks at redshift of 1.5 and falls off rapidly beyond redshift 2.5. We also include an example application of this dataset for redshift estimation, demonstrating that using images for redshift estimation produces more accurate results compared to using photometry alone. For example, the bias in redshift estimate is a factor of 10 lower when using images between redshift of 0.1 to 1.25 compared to photometry alone. Results from dataset such as this will help inform us on how to best make use of data from the next generation of galaxy surveys.

Figures (6)

• Figure 1: Example of galaxies at different redshifts from the GalaxiesML dataset. The top row shows the images in a linear intensity scale while the bottom row shows the images in a logarithmic scale to show lower surface brightness features like nearby galaxies .
• Figure 2: Flow chart showing the steps used in creating the GalaxiesML dataset. Rectangles represent processes and parallelograms are the products. The green parallelograms are the datasets that are part of the release.
• Figure 3: Example of the morphological parameters measured on a low redshift galaxy (Object ID 36416246018753893, $z = 0.0713$) using Source Extractor. Left: isophototal area, center: ellipticity, right: Sersic Index.
• Figure 4: Visualization of predicted photo-zs vs. measured spectroscopic redshifts for a non-probabilistic neural network (top left), a Bayesian neural network (top right), and two previously proposed ML models (bottom left and right). Figure from jones2022
• Figure 5: CNN architecture for this work. The model includes both images and photometry.