The DREAMS project

DREAMS stands for DaRk mattEr with AI and siMulationS, and it is a project designed to combine astrophysics with particle physics through machine learning in order to shed light on the nature of dark matter and to learn about the physics that shapes the Universe on small scales. For this purpose, DREAMS will generate thousands of state-of-the-art hydrodynamic simulations with different astrophysics and dark matter models on different environments.


The above image shows hundreds of Milky-Way like galaxies from DREAMS both face-on and edge-on. Each galaxy was created by running a zoom-in simulation with a different warm dark matter mass and different feedback efficiency from supernovae and super massive black-holes. The simulations are designed to be analyze with machine learning techniques in order to extract the maximum information from the data while marginalizing over uncertain astrophysical effects.