Domain adaptation techniques for improved cross-domain study of galaxy mergers

TL;DR

This paper explores how domain adaptation techniques like MMD and DANN can improve neural network performance in classifying galaxy mergers across simulated and real astronomical data, addressing domain shift challenges.

Contribution

It demonstrates the effectiveness of MMD and DANN domain adaptation methods in astronomy for cross-domain galaxy merger classification, a novel application in this field.

Findings

MMD and DANN significantly improve classifier accuracy on target domain.

Domain adaptation techniques outperform conventional machine learning methods.

Results show promise for applying deep learning to real astronomical observations.

Abstract

In astronomy, neural networks are often trained on simulated data with the prospect of being applied to real observations. Unfortunately, simply training a deep neural network on images from one domain does not guarantee satisfactory performance on new images from a different domain. The ability to share cross-domain knowledge is the main advantage of modern deep domain adaptation techniques. Here we demonstrate the use of two techniques - Maximum Mean Discrepancy (MMD) and adversarial training with Domain Adversarial Neural Networks (DANN) - for the classification of distant galaxy mergers from the Illustris-1 simulation, where the two domains presented differ only due to inclusion of observational noise. We show how the addition of either MMD or adversarial training greatly improves the performance of the classifier on the target domain when compared to conventional machine learning algorithms, thereby demonstrating great promise for their use in astronomy.