Unsupervised Domain Adaptation for Constraining Star Formation Histories
This addresses the challenge for astronomers in understanding galaxy formation by providing a more reliable method to derive SFHs from spectral energy distributions, though it is incremental as it focuses on simulated data as an initial phase.
The paper tackles the problem of inferring star formation histories (SFHs) for galaxies from observational data, where ground-truth SFHs are unavailable, by using unsupervised domain adaptation with simulated data as a first step, achieving improved accuracy over traditional Bayesian methods.
The prevalent paradigm of machine learning today is to use past observations to predict future ones. What if, however, we are interested in knowing the past given the present? This situation is indeed one that astronomers must contend with often. To understand the formation of our universe, we must derive the time evolution of the visible mass content of galaxies. However, to observe a complete star life, one would need to wait for one billion years! To overcome this difficulty, astrophysicists leverage supercomputers and evolve simulated models of galaxies till the current age of the universe, thus establishing a mapping between observed radiation and star formation histories (SFHs). Such ground-truth SFHs are lacking for actual galaxy observations, where they are usually inferred -- with often poor confidence -- from spectral energy distributions (SEDs) using Bayesian fitting methods. In this investigation, we discuss the ability of unsupervised domain adaptation to derive accurate SFHs for galaxies with simulated data as a necessary first step in developing a technique that can ultimately be applied to observational data.