A volumetric deep Convolutional Neural Network for simulation of mock dark matter halo catalogues
This provides a fast and efficient method for generating mock simulations for astrophysics researchers, reducing computational costs compared to traditional N-body simulations.
The authors tackled the problem of generating mock dark matter halo catalogues for large-scale structure surveys by training a 3D convolutional neural network to identify protohalos from cosmological initial conditions, achieving a Dice coefficient of ~92% and matching mass functions and power spectra to within ~10% of ground truth simulations.
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.