Learning Neutrino Effects in Cosmology with Convolutional Neural Network

Measuring the sum of the three active neutrino masses, M ( nu ), is one of the most important challenges in modern cosmology. Massive neutrinos imprint characteristic signatures on several cosmological observables, in particular, on the large-scale structure of the universe. In order to maximize the information that can be retrieved from galaxy surveys, accurate theoretical predictions in the nonlinear regime are needed. Currently, one way to achieve those predictions is by running cosmological numerical simulations. Unfortunately, producing those simulations requires high computational resources-several hundred to thousand core hours for each neutrino mass case. In this work, we propose a new method, based on a deep-learning network ((DM)-M-3), to quickly generate simulations with massive neutrinos from standard ?CDM simulations without neutrinos. We computed multiple relevant statistical measures of deep-learning generated simulations and conclude that our approach is an accurate alternative to the traditional N-body techniques. In particular the power spectrum is within similar or equal to 6% down to nonlinear scales k = 0.7 h Mpc(-1). Finally, our method allows us to generate massive neutrino simulations 10,000 times faster than the traditional methods.