An interpretable machine learning framework for dark matter halo formation

Abstract

We present a generalization of our recently proposed machine learning framework, aiming to provide new physical insights into dark matter halo formation. We investigate the impact of the initial density and tidal shear fields on the formation of haloes over the mass range $11.4\le \log (M/M_{\odot })\le 13.4$. The algorithm is trained on an N-body simulation to infer the final mass of the halo to which each dark matter particle will later belong. We then quantify the difference in the predictive accuracy between machine learning models using a metric based on the Kullback-Leibler divergence. We first train the algorithm with information about the density contrast in the particles' local environment. The addition of tidal shear information does not yield an improved halo collapse model over one based on density information alone; the difference in their predictive performance is consistent with the statistical uncertainty of the density-only based model. This implies that our machine learning setup does not identify any significant role for the tidal shear in determining halo masses. This result is confirmed as we verify the ability of the initial conditions-to-halo mass mapping learnt from one simulation to generalize to independent simulations. Our work illustrates the broader potential of developing interpretable machine learning frameworks to gain physical understanding of non-linear large-scale structure formation.

arXiv comment13 pages, 8 figures. Minor changes to match version published in MNRAS. Accepted on 12/09/2019

References in corpus (12)

• The cosmological simulation code GADGET-2
• Simulating the joint evolution of quasars, galaxies and their large-scale distribution
• Large scale bias and the peak background split
• Ellipsoidal collapse and an improved model for the number and spatial distribution of dark matter haloes
• Five-Year Wilkinson Microwave Anisotropy Probe (WMAP) Observations: Likelihoods and Parameters from the WMAP data
• GADGET: A code for collisionless and gasdynamical cosmological simulations
• Concentrations of Dark Halos from their Assembly Histories
• The Merger Rates and Mass Assembly Histories of Dark Matter Haloes in the Two Millennium Simulations
• The halo merger rate in the Millennium Simulation and implications for observed galaxy merger fractions
• Machine learning cosmological structure formation
• A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
• On the dissection of degenerate cosmologies with machine learning

Cited by in corpus (32)

• A machine learning approach to mapping baryons onto dark matter haloes using the EAGLE and C-EAGLE simulations
• Relating the structure of dark matter halos to their assembly and environment
• Predicting dark matter halo formation in N-body simulations with deep regression networks
• Baryon acoustic oscillations reconstruction using convolutional neural networks
• Cosmic Velocity Field Reconstruction Using AI
• Measuring the Hubble Constant with cosmic chronometers: a machine learning approach
• (DarkAI) Mapping the large-scale density field of dark matter using artificial intelligence
• Insights into the origin of halo mass profiles from machine learning
• A semi-supervised approach to dark matter searches in direct detection data with machine learning
• Stellar angular momentum can be controlled from cosmological initial conditions
• Towards Accurate Field-Level Inference of Massive Cosmic Structures
• Halo assembly bias from a deep learning model of halo formation
• Estimation of the masses in the Local Group by Gradient Boosted Decision Trees
• Bayesian Control Variates for optimal covariance estimation with pairs of simulations and surrogates
• Deep learning insights into cosmological structure formation
• The causal effect of environment on halo mass and concentration
• Machine learning prediction for mean motion resonance behaviour -- The planar case
• Machine Learning the Fates of Dark Matter Subhalos: A Fuzzy Crystal Ball
• Massive $\nu$s through the CNN lens: interpreting the field-level neutrino mass information in weak lensing
• Multi-Epoch Machine Learning 2: Identifying physical drivers of galaxy properties in simulations
• Accurate halo mass functions from the simplest excursion set theory
• Interpreting Cosmological Information from Neural Networks in the Hydrodynamic Universe
• Large-step neural network for learning the symplectic evolution from partitioned data
• Non-parametric Lagrangian biasing from the insights of neural nets
• Excursion Sets with a "Perfect" Collapse Model
• Cosmological parameter estimation from large-scale structure deep learning
• Cosmic velocity, density and halo mass function: Insights from deep learning
• Mimicking the halo-galaxy connection using machine learning
• DeepVoid: A Deep Learning Void Detector
• Segmenting proto-halos with vision transformers
• Assessing Galaxy Rotation Kinematics: Insights from Convolutional Neural Networks on Velocity Variations
• Discovering the building blocks of dark matter halo density profiles with neural networks