Insights on Galaxy Evolution from Interpretable Sparse Feature Networks
This addresses the problem of interpretability in machine learning for astronomers analyzing galaxy evolution, though it is incremental as it builds on existing methods for specific tasks.
The paper tackles the lack of interpretability in deep neural networks for predicting galaxy properties from images by introducing Sparse Feature Networks (SFNets), which produce interpretable features without sacrificing accuracy, performing comparably to state-of-the-art models.
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.