A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues

TL;DR

This paper introduces a 3D deep CNN trained on semi-analytic halo catalogues to efficiently predict dark matter halos from initial conditions, achieving high accuracy and matching key statistical properties of full simulations.

Contribution

It presents a novel deep learning approach for fast, accurate halo catalog generation directly from initial conditions, reducing reliance on expensive N-body simulations.

Findings

Achieved ~92% Dice coefficient in halo identification

Predicted halo catalogues match mass function and power spectra within ~10%

Network predictions align with non-linear ellipsoidal collapse models

Abstract

For modern large-scale structure survey techniques it has become standard practice to test data analysis pipelines on large suites of mock simulations, a task which is currently prohibitively expensive for full N-body simulations. Instead of calculating this costly gravitational evolution, we have trained a three-dimensional deep Convolutional Neural Network (CNN) to identify dark matter protohalos directly from the cosmological initial conditions. Training on halo catalogues from the Peak Patch semi-analytic code, we test various CNN architectures and find they generically achieve a Dice coefficient of ~92% in only 24 hours of training. We present a simple and fast geometric halo finding algorithm to extract halos from this powerful pixel-wise binary classifier and find that the predicted catalogues match the mass function and power spectra of the ground truth simulations to within ~10%. We investigate the effect of long-range tidal forces on an object-by-object basis and find that the network's predictions are consistent with the non-linear ellipsoidal collapse equations used explicitly by the Peak Patch algorithm.