Cosmological Field Emulation and Parameter Inference with Diffusion Models
This work addresses computational challenges in cosmology by providing efficient emulation and inference tools, though it is incremental as it applies existing diffusion models to this domain.
The authors tackled the problem of cosmological simulation by using diffusion generative models to emulate cold dark matter density fields conditional on cosmological parameters and to infer parameters from input fields, showing the model generates fields with consistent power spectra and obtains tight constraints on parameters.
Cosmological simulations play a crucial role in elucidating the effect of physical parameters on the statistics of fields and on constraining parameters given information on density fields. We leverage diffusion generative models to address two tasks of importance to cosmology -- as an emulator for cold dark matter density fields conditional on input cosmological parameters $Ω_m$ and $σ_8$, and as a parameter inference model that can return constraints on the cosmological parameters of an input field. We show that the model is able to generate fields with power spectra that are consistent with those of the simulated target distribution, and capture the subtle effect of each parameter on modulations in the power spectrum. We additionally explore their utility as parameter inference models and find that we can obtain tight constraints on cosmological parameters.