DeepShadows: Separating Low Surface Brightness Galaxies from Artifacts using Deep Learning
This work provides a more efficient and accurate method for identifying low-surface-brightness galaxies, which is crucial for astronomers studying the faint universe, especially with the advent of future large-scale surveys that will generate petabytes of data.
This paper addresses the challenge of distinguishing low-surface-brightness galaxies (LSBGs) from artifacts in galaxy survey images, a task currently reliant on time-consuming visual inspection. The authors developed DeepShadows, a convolutional neural network, which achieved a test accuracy of 92.0% on Dark Energy Survey data, outperforming feature-based machine learning models. DeepShadows also demonstrated adaptability to the Hyper-Suprime-Cam survey via transfer learning, reaching 87.6% accuracy after retraining on a small sample.
Searches for low-surface-brightness galaxies (LSBGs) in galaxy surveys are plagued by the presence of a large number of artifacts (e.g., objects blended in the diffuse light from stars and galaxies, Galactic cirrus, star-forming regions in the arms of spiral galaxies, etc.) that have to be rejected through time consuming visual inspection. In future surveys, which are expected to collect hundreds of petabytes of data and detect billions of objects, such an approach will not be feasible. We investigate the use of convolutional neural networks (CNNs) for the problem of separating LSBGs from artifacts in survey images. We take advantage of the fact that, for the first time, we have available a large number of labeled LSBGs and artifacts from the Dark Energy Survey, that we use to train, validate, and test a CNN model. That model, which we call DeepShadows, achieves a test accuracy of $92.0 \%$, a significant improvement relative to feature-based machine learning models. We also study the ability to use transfer learning to adapt this model to classify objects from the deeper Hyper-Suprime-Cam survey, and we show that after the model is retrained on a very small sample from the new survey, it can reach an accuracy of $87.6\%$. These results demonstrate that CNNs offer a very promising path in the quest to study the low-surface-brightness universe.