Insights on Galaxy Evolution from Interpretable Sparse Feature Networks

TL;DR

This paper introduces SFNet, an interpretable neural network architecture that effectively predicts galaxy properties from images without sacrificing accuracy, aiding understanding of galaxy evolution.

Contribution

The paper proposes SFNet, a novel neural network that produces interpretable features for galaxy property prediction, bridging the gap between accuracy and interpretability in astronomical imaging.

Findings

SFNet achieves comparable accuracy to state-of-the-art models.

SFNet's features are interpretable and linearly combinable.

The approach aids in understanding physical patterns in galaxy data.

Abstract

Galaxy appearances reveal the physics of how they formed and evolved. Machine learning models can now exploit galaxies' information-rich morphologies to predict physical properties directly from image cutouts. Learning the relationship between pixel-level features and galaxy properties is essential for building a physical understanding of galaxy evolution, but we are still unable to explicate the details of how deep neural networks represent image features. To address this lack of interpretability, we present a novel neural network architecture called a Sparse Feature Network (SFNet). SFNets produce interpretable features that can be linearly combined in order to estimate galaxy properties like optical emission line ratios or gas-phase metallicity. We find that SFNets do not sacrifice accuracy in order to gain interpretability, and that they perform comparably well to cutting-edge models on astronomical machine learning tasks. Our novel approach is valuable for finding physical patterns in large datasets and helping astronomers interpret machine learning results.