Finding universal relations in subhalo properties with artificial intelligence

Abstract

We use a generic formalism designed to search for relations in high-dimensional spaces to determine if the total mass of a subhalo can be predicted from other internal properties such as velocity dispersion, radius, or star-formation rate. We train neural networks using data from the Cosmology and Astrophysics with MachinE Learning Simulations (CAMELS) project and show that the model can predict the total mass of a subhalo with high accuracy: more than 99% of the subhalos have a predicted mass within 0.2 dex of their true value. The networks exhibit surprising extrapolation properties, being able to accurately predict the total mass of any type of subhalo containing any kind of galaxy at any redshift from simulations with different cosmologies, astrophysics models, subgrid physics, volumes, and resolutions, indicating that the network may have found a universal relation. We then use different methods to find equations that approximate the relation found by the networks and derive new analytic expressions that predict the total mass of a subhalo from its radius, velocity dispersion, and maximum circular velocity. We show that in some regimes, the analytic expressions are more accurate than the neural networks. We interpret the relation found by the neural network and approximated by the analytic equation as being connected to the virial theorem.

23 pages, 15 figures

References in corpus (2)

• Simulating galaxy formation with black hole driven thermal and kinetic feedback
• Simba: Cosmological Simulations with Black Hole Growth and Feedback

Cited by in corpus (23)

• Deep symbolic regression for physics guided by units constraints: toward the automated discovery of physical laws
• The CAMELS project: public data release
• Learning cosmology and clustering with cosmic graphs
• Robust Field-level Likelihood-free Inference with Galaxies
• Cosmology with one galaxy?
• Machine Learning for Observational Cosmology
• The scatter in the galaxy-halo connection: a machine learning analysis
• The SZ flux-mass ($Y$-$M$) relation at low halo masses: improvements with symbolic regression and strong constraints on baryonic feedback
• Augmenting astrophysical scaling relations with machine learning: application to reducing the Sunyaev-Zeldovich flux-mass scatter
• Fast and realistic large-scale structure from machine-learning-augmented random field simulations
• Percent-level constraints on baryonic feedback with spectral distortion measurements
• Not Hydro: Using Neural Networks to estimate galaxy properties on a Dark-Matter-Only simulation
• SymbolNet: Neural Symbolic Regression with Adaptive Dynamic Pruning for Compression
• CASCO: Cosmological and AStrophysical parameters from Cosmological simulations and Observations -- I. Constraining physical processes in local star-forming galaxies
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• SymbolFit: Automatic Parametric Modeling with Symbolic Regression
• Total and dark mass from observations of galaxy centers with Machine Learning
• Machine Learning-Based Analytical Expressions for Gray-Body Factors and Application to Primordial Black Holes
• Multi-Epoch Machine Learning 2: Identifying physical drivers of galaxy properties in simulations
• Neural Network Analysis of S-Star Dynamics: Implications for Modified Gravity
• kSZ Pairwise Velocity Reconstruction with Machine Learning
• Inferring halo masses with Graph Neural Networks
• Spatially resolved stellar-to-total dynamical mass relation: Radial variations, gradients and profiles of galaxy stellar populations