%0 Journal Article
%T Weighing the Milky Way and Andromeda galaxies with artificial intelligence
%A Villanueva-Domingo, P.
%A Villaescusa-Navarro, F.
%A Genel, S.
%A Angles-Alcazar, D.
%A Hernquist, L.
%A Marinacci, F.
%A Spergel, D. N.
%A Vogelsberger, M.
%A Narayanan, D.
%J Physical Review D
%D 2023
%V 107
%N 10
%I Amer Physical Soc
%@ 2470-0010
%G English
%F Villanueva-Domingo_etal2023
%O WOS:000988340900001
%O exported from refbase (https://references.ific.uv.es/refbase/show.php?record=5539), last updated on Sun, 11 Jun 2023 17:47:04 +0000
%X We present new constraints on the masses of the halos hosting the Milky Way and Andromeda galaxies derived using graph neural networks. Our models, trained on 2,000 state-of-the-art hydrodynamic simulations of the CAMELS project, only make use of the positions, velocities and stellar masses of the galaxies belonging to the halos, and are able to perform likelihood-free inference on halo masses while accounting for both cosmological and astrophysical uncertainties. Our constraints are in agreement with estimates from other traditional methods, within our derived posterior standard deviation.
%R 10.1103/PhysRevD.107.103003
%U https://arxiv.org/abs/2111.14874
%U https://doi.org/10.1103/PhysRevD.107.103003
%P 103003-8pp