Abstract：Upcoming cosmological surveys, such as the China Space Station Telescope and the Roman Space Telescope, will deliver unprecedented data for studies of the large-scale structure of the Universe. These observations will shed new light on cosmic evolution and the nature of its fundamental components, including dark matter and dark energy. To fully exploit this wealth of data and constrain cosmological models, we need accurate and efficient theoretical predictions across a high-dimensional parameter space.
To address this challenge, we performed the Goku simulation suite—the first N-body simulation suite spanning 10 cosmological parameters, including the five standard ΛCDM parameters and extensions that account for dynamical dark energy, massive neutrinos, the effective number of neutrino, and the running of the primordial spectral index. Building on this suite, we trained GokuNEmu, a state-of-the-art emulator for the nonlinear matter power spectrum, using advanced multifidelity machine learning techniques designed for cosmological emulation. GokuNEmu achieves offers a uniquely powerful tool for the analysis forthcoming survey data.
Bio：Yanhui Yang is a fourth-year Ph.D. student in theoretical astrophysics/cosmology at University of California, Riverside. His research interests include the large-scale structure of the Universe and galaxy evolution. Previously, He received his bachelor's degree in Astronomy from University of Science and Technology of China in 2021.