Inferring halo masses with Graph Neural Networks
arXiv:2111.08683 · doi:10.3847/1538-4357/ac7aa3
Abstract
Understanding the halo-galaxy connection is fundamental in order to improve our knowledge on the nature and properties of dark matter. In this work we build a model that infers the mass of a halo given the positions, velocities, stellar masses, and radii of the galaxies it hosts. In order to capture information from correlations among galaxy properties and their phase-space, we use Graph Neural Networks (GNNs), that are designed to work with irregular and sparse data. We train our models on galaxies from more than 2,000 state-of-the-art simulations from the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project. Our model, that accounts for cosmological and astrophysical uncertainties, is able to constrain the masses of the halos with a 0.2 dex accuracy. Furthermore, a GNN trained on a suite of simulations is able to preserve part of its accuracy when tested on simulations run with a different code that utilizes a distinct subgrid physics model, showing the robustness of our method. The PyTorch Geometric implementation of the GNN is publicly available on Github at https://github.com/PabloVD/HaloGraphNet
20 pages, 8 figures, code publicly available at https://github.com/PabloVD/HaloGraphNet
References in corpus (23)
- Semi-Supervised Classification with Graph Convolutional Networks
- Properties of galaxies reproduced by a hydrodynamic simulation
- Simulating galaxy formation with black hole driven thermal and kinetic feedback
- Simba: Cosmological Simulations with Black Hole Growth and Feedback
- Captum: A unified and generic model interpretability library for PyTorch
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Dark Halos of M31 and the Milky Way
- Physical properties underlying observed kinematics of satellite galaxies
- Galaxy Cluster Mass Reconstruction Project: II. Quantifying scatter and bias using contrasting mock catalogues
- The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
- Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
- Finding universal relations in subhalo properties with artificial intelligence
- Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
- Learning Symbolic Physics with Graph Networks
- The Outer Stellar Mass of Massive Galaxies: A Simple Tracer of Halo Mass with Scatter Comparable to Richness and Reduced Projection Effects
- Inferring galaxy dark halo properties from visible matter with Machine Learning
- Modeling assembly bias with machine learning and symbolic regression
- Solving high-dimensional parameter inference: marginal posterior densities & Moment Networks
- Tracing Dark Matter Halos with Satellite Kinematics and the Central Stellar Velocity Dispersion of Galaxies
- Galaxy Halo Masses from Weak Gravitational Lensing
- Mass Estimation of Planck Galaxy Clusters using Deep Learning
- Weighing the Milky Way and Andromeda with Artificial Intelligence
- Success of Machine Learning algorithms in Dynamical Mass Measurements of Galaxy Clusters