Machine Learning and Cosmological Simulations
Harshil Kamdar, Harvard University
We explore the application of machine learning (ML) to the problem of galaxy formation and evolution in a hierarchical universe. Our motivations are two-fold: first, presenting a new, promising technique to study galaxy formation; and second, quantitatively evaluating the extent of the influence of dark matter halo properties on small-scale structure formation. For our analyses, we use both semi-analytical models (Millennium simulation) and N-body plus hydrodynamical simulations (Illustris simulation). The ML algorithms are trained on important dark matter halo properties (inputs) and galaxy properties (outputs). The trained models are able to robustly predict the gas mass, stellar mass, black hole mass, star formation rate, g-r color, and stellar metallicity. Moreover, the ML-simulated galaxies obey fundamental observational constraints, implying that the population of ML-predicted galaxies is physically and statistically robust. Next, ML algorithms are trained on an N-body plus hydrodynamical simulation and applied to an N-body-only simulation (Dark Sky simulation, Illustris Dark), populating this new simulation with galaxies. We can examine how structure formation changes with different cosmological parameters and are able to mimic a full-blown hydrodynamical simulation in a computation time that is orders of magnitude smaller. We find that the set of ML-simulated galaxies in Dark Sky obey the same observational constraints, further solidifying ML's place as an intriguing and promising technique in future galaxy-formation studies and rapid mock-galaxy catalog creation.
Abstract Author(s): Harshil Kamdar, Matthew Turk, Robert Brunner