From Dark Matter to Galaxies with Convolutional Neural Networks
This addresses the problem of high computational costs in cosmology for researchers, though it is incremental as it builds on existing deep learning methods.
The paper tackles the computational expense of cosmological simulations by using a deep learning approach to map from cheaper dark-matter-only simulations to galaxy distributions, outperforming a state-of-the-art model with a good trade-off between cost and accuracy.
Cosmological simulations play an important role in the interpretation of astronomical data, in particular in comparing observed data to our theoretical expectations. However, to compare data with these simulations, the simulations in principle need to include gravity, magneto-hydrodyanmics, radiative transfer, etc. These ideal large-volume simulations (gravo-magneto-hydrodynamical) are incredibly computationally expensive which can cost tens of millions of CPU hours to run. In this paper, we propose a deep learning approach to map from the dark-matter-only simulation (computationally cheaper) to the galaxy distribution (from the much costlier cosmological simulation). The main challenge of this task is the high sparsity in the target galaxy distribution: space is mainly empty. We propose a cascade architecture composed of a classification filter followed by a regression procedure. We show that our result outperforms a state-of-the-art model used in the astronomical community, and provides a good trade-off between computational cost and prediction accuracy.