Deep Learning Segmentation of Spiral Arms and Bars
This provides a scalable, high-precision tool for astronomers to study galactic evolution, though it is incremental as it applies deep learning to a specific domain problem.
The authors tackled the problem of segmenting galactic spiral arms and bars by developing the first deep learning model for this task, achieving expert preference over existing methods in 99% of evaluations and high-quality ratings in 89% of evaluations.
We present the first deep learning model for segmenting galactic spiral arms and bars. In a blinded assessment by expert astronomers, our predicted spiral arm masks are preferred over both current automated methods (99% of evaluations) and our original volunteer labels (79% of evaluations). Experts rated our spiral arm masks as `mostly good' to `perfect' in 89% of evaluations. Bar lengths trivially derived from our predicted bar masks are in excellent agreement with a dedicated crowdsourcing project. The pixelwise precision of our masks, previously impossible at scale, will underpin new research into how spiral arms and bars evolve.