2023MNRAS.526.5735T

Globular clusters (GCs) are powerful tracers of the galaxy assembly process, and have already been used to obtain a detailed picture of the progenitors of the Milky Way (MW). Using the E-MOSAICS cosmological simulation of a (34.4 Mpc)³ volume that follows the formation and co-evolution of galaxies and their star cluster populations, we develop a method to link the origin of GCs to their observable properties. We capture this complex link using a supervised deep learning algorithm trained on the simulations, and predict the origin of individual GCs (whether they formed in the main progenitor or were accreted from satellites) based solely on extragalactic observables. An artificial neural network classifier trained on ∼50 000 GCs hosted by ∼700 simulated galaxies successfully predicts the origin of GCs in the test set with a mean accuracy of 89 per cent for the objects with $\rm [Fe/H]\lt -0.5$ that have unambiguous classifications. The network relies mostly on the alpha-element abundances, metallicities, projected positions, and projected angular momenta of the clusters to predict their origin. A real-world test using the known progenitor associations of the MW GCs achieves up to 90 per cent accuracy, and successfully identifies as accreted most of the GCs in the inner Galaxy associated to the Kraken progenitor, as well as all the Gaia-Enceladus GCs. We demonstrate that the model is robust to observational uncertainties, and develop a method to predict the classification accuracy across observed galaxies. The classifier can be optimized for available observables (e.g. to improve the accuracy by including GC ages), making it a valuable tool to reconstruct the assembly histories of galaxies in upcoming wide-field surveys.