Journal
MONTHLY NOTICES OF THE ROYAL ASTRONOMICAL SOCIETY
Volume 482, Issue 3, Pages 2861-2871Publisher
OXFORD UNIV PRESS
DOI: 10.1093/mnras/sty2949
Keywords
methods: numerical; galaxies: haloes; dark matter; large-scale structure of Universe
Categories
Funding
- NSERC
- Canada Foundation for Innovation under Compute Canada
- Government of Ontario
- Ontario Research Fund - Research Excellence
- University of Toronto
Ask authors/readers for more resources
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 protohaloes 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 similar to 92 per cent in only 24 h of training. We present a simple and fast geometric halo finding algorithm to extract haloes 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 similar to 10 per cent. 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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available