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
arXiv comment20 pages, 8 figures, code publicly available at https://github.com/PabloVD/HaloGraphNet
References in corpus (58)
- Semi-Supervised Classification with Graph Convolutional Networks
- The cosmological simulation code GADGET-2
- Populating a cluster of galaxies - I. Results at z=0
- Simulating Galaxy Formation with the IllustrisTNG Model
- First results from the IllustrisTNG simulations: matter and galaxy clustering
- Physical Models of Galaxy Formation in a Cosmological Framework
- Graph Neural Networks: A Review of Methods and Applications
- Properties of galaxies reproduced by a hydrodynamic simulation
- First results from the IllustrisTNG simulations: A tale of two elements -- chemical evolution of magnesium and europium
- Simulating galaxy formation with black hole driven thermal and kinetic feedback
- GIZMO: A New Class of Accurate, Mesh-Free Hydrodynamic Simulation Methods
- Simba: Cosmological Simulations with Black Hole Growth and Feedback
- First results from the IllustrisTNG simulations: radio haloes and magnetic fields
- A Comprehensive Analysis of Uncertainties Affecting the Stellar Mass - Halo Mass Relation for 0<z<4
- A model for cosmological simulations of galaxy formation physics
- Rotation Curves of Spiral Galaxies
- Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
- The Connection between Galaxies and their Dark Matter Halos
- Captum: A unified and generic model interpretability library for PyTorch
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- The Arepo public code release
- MUFASA: Galaxy Formation Simulations With Meshless Hydrodynamics
- The CAMELS project: Cosmology and Astrophysics with MachinE Learning Simulations
- Gravitational torque-driven black hole growth and feedback in cosmological simulations
- Graph Neural Networks in Particle Physics
- Galaxy Cluster Gas Mass Fractions from Sunyaev-Zel'dovich Effect Measurements: Constraints on Omega_M
- Toward Unbiased Galaxy Cluster Masses from Line of Sight Velocity Dispersions
- Likelihood-free inference with neural compression of DES SV weak lensing map statistics
- 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
- A Deep Learning Approach to Galaxy Cluster X-ray Masses
- A Machine Learning Approach for Dynamical Mass Measurements of Galaxy Clusters
- A Robust and Efficient Deep Learning Method for Dynamical Mass Measurements of Galaxy Clusters
- The CAMELS Multifield Dataset: Learning the Universe's Fundamental Parameters with Artificial Intelligence
- Dynamical Mass Measurements of Contaminated Galaxy Clusters Using Machine Learning
- Weak Lensing Reveals a Tight Connection Between Dark Matter Halo Mass and the Distribution of Stellar Mass in Massive Galaxies
- Prediction of galaxy halo masses in SDSS DR7 via a machine learning approach
- Chandra Measurements of a Complete Sample of X-ray Luminous Galaxy Clusters: the Gas Mass Fraction
- An application of machine learning techniques to galaxy cluster mass estimation using the MACSIS simulations
- Galaxy cluster mass estimation with deep learning and hydrodynamical simulations
- Removing Astrophysics in 21 cm maps with Neural Networks
- Dynamical mass inference of galaxy clusters with neural flows
- Using X-Ray Morphological Parameters to Strengthen Galaxy Cluster Mass Estimates via Machine Learning
- Finding universal relations in subhalo properties with artificial intelligence
- Learning Symbolic Physics with Graph Networks
- Simulation-based inference of dynamical galaxy cluster masses with 3D convolutional neural networks
- The Fundamental Relation between Halo Mass and Galaxy Group Properties
- 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
- Deep learning insights into cosmological structure formation
- 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