Galaxy Morphology Classification with Counterfactual Explanation
This addresses the need for explainable AI in astronomy for researchers analyzing large galaxy datasets, though it is incremental as it builds on existing encoder-decoder and flow-based methods.
The paper tackles the problem of classifying galaxy morphologies with machine learning by proposing an encoder-decoder architecture extended with invertible flow to improve predictive performance and provide counterfactual explanations for better interpretability.
Galaxy morphologies play an essential role in the study of the evolution of galaxies. The determination of morphologies is laborious for a large amount of data giving rise to machine learning-based approaches. Unfortunately, most of these approaches offer no insight into how the model works and make the results difficult to understand and explain. We here propose to extend a classical encoder-decoder architecture with invertible flow, allowing us to not only obtain a good predictive performance but also provide additional information about the decision process with counterfactual explanations.