Classifying Metal-poor Stars with Machine Learning Using Nucleosynthesis Calculations

Abstract We apply the capabilities of machine learning (ML) to discern patterns in order to classify metal-poor stars. To do so, we train an ML model on a bank of nucleosynthesis calculations derived from hydrodynamic simulations for events such as neutron star mergers where the rapid ( r ) neutron capture process can take place. Likewise, we consider a bank of calculations from simulations of the slow ( s ) neutron capture process. We explore the performance of both a binary classifier and a one-class classifier. We demonstrate that our ML models do well overall in recognizing the s process from the r process, and after training on theoretical calculations, ML stellar assignments match conventional labels 87% of the time. We highlight that this method then points to stars that could benefit from additional observational measurements. We then apply the one-class classifier to numerous cases on which it did not train, including i -process stars, and a few nucleosynthesis predictions for the i process in rapidly accreting white dwarfs and r process in MHD supernovae. We demonstrate that the ML assigns some of the presently considered i -process stars to instead be of r or s in origin but likewise finds stars currently labeled as s to be potentially more aligned with i enrichment. This first application of ML to classify metal-poor star enrichment using theoretical nucleosynthesis calculations reveals the promise, and some challenges, associated with this new data-driven path forward.