Skip to main content
SearchLoginLogin or Signup

Measuring Galactic Dark Matter through Unsupervised Machine Learning

Presentation #347.07 in the session Dark Matter & Dark Energy — iPoster Session.

Published onJun 29, 2022
Measuring Galactic Dark Matter through Unsupervised Machine Learning

Measuring the density profile of dark matter in the Solar neighborhood has important implications for both dark matter theory and experiment. In this work, we apply autoregressive flows to stars from a realistic simulation of a Milky Way-type galaxy to learn – in an unsupervised way – the stellar phase-space density and its derivatives. With these as inputs, and under the assumption of dynamic equilibrium, the gravitational acceleration field and dark matter density can be calculated directly from the Boltzmann Equation without the need to assume either cylindrical symmetry or specific functional forms for the dark matter density. We demonstrate our approach can accurately reconstruct the density and acceleration profiles of the simulated galaxy, including Gaia-like errors in the kinematic measurements. We also quantify the statistical and measurement uncertainties of our machine learning-based estimations using resampling methods.

No comments here