Quantifying the fine structures of disk galaxies with deep learning:Segmentation of spiral arms in different Hubble types

TL;DR

This paper applies deep learning, specifically U-net, to segment spiral arms in disk galaxies, enabling detailed analysis of their structure and role in galaxy evolution.

Contribution

It introduces a novel application of U-net for galaxy spiral arm segmentation, advancing automated analysis in astrophysics.

Findings

Successful segmentation of spiral arms in various galaxy types

Enhanced understanding of spiral arms' spatial correlations with galactic components

Potential for large-scale galaxy structure analysis

Abstract

Spatial correlations between spiral arms and other galactic components such as giant molecular clouds and massive OB stars suggest that spiral arms can play vital roles in various aspects of disk galaxy evolution. Segmentation of spiral arms in disk galaxies is therefore a key task to investigate these correlations. We here try to decompose disk galaxies into spiral and non-spiral regions by using U-net, which is based on deep learning algorithms and has been invented for segmentation tasks in biology.