Pushing automated morphological classifications to their limits with the Dark Energy Survey

We present morphological classifications of similar to 27 million galaxies from the Dark Energy Survey (DES) Data Release 1 (DR1) using a supervised deep learning algorithm. The classification scheme separates: (a) early-type galaxies (ETGs) from late-type galaxies (LTGs); and (b) face-on galaxies from edge-on. Our convolutional neural networks (CNNs) are trained on a small subset of DES objects with previously known classifications. These typically have m(r) less than or similar to 17.7 mag; we model fainter objects to m(r) < 21.5 mag by simulating what the brighter objects with well-determined classifications would look like if they were at higher redshifts. The CNNs reach 97 percent accuracy to m(r) < 21.5 on their training sets, suggesting that they are able to recover features more accurately than the human eye. We then used the trained CNNs to classify the vast majority of the other DES images. The final catalogue comprises five independent CNN predictions for each classification scheme, helping to determine if the CNN predictions are robust or not. We obtain secure classifications for similar to 87 percent and 73 percent of the catalogue for the ETG versus LTG and edge-on versus face-on models, respectively. Combining the two classifications (a) and (b) helps to increase the purity of the ETG sample and to identify edge-on lenticular galaxies (as ETGs with high ellipticity). Where a comparison is possible, our classifications correlate very well with Sersic index (n), ellipticity (E), and spectral type, even for the fainter galaxies. This is the largest multiband catalogue of automated galaxy morphologies to date.

Automated summary

In this study, a supervised deep learning algorithm was used to classify morphologies of approximately 27 million galaxies from the Dark Energy Survey. The convolutional neural networks (CNNs) reached high accuracy and were able to recover features more accurately than the human eye, with secure classifications obtained for a large percentage of the catalog. Combining two classification schemes increased sample purity and identified edge-on lenticular galaxies, resulting in the largest multiband automated galaxy morphology catalog to date.