Can denoising diffusion probabilistic models generate realistic astrophysical fields?
This work addresses the problem of generating and denoising astrophysical data for researchers in astronomy, but it is incremental as it applies existing methods to new domains.
The study investigated whether denoising diffusion probabilistic models can generate realistic astrophysical fields, such as dark matter density and interstellar dust images, and demonstrated a proof-of-concept for denoising dust images, marking the first application of these models to the interstellar medium.
Score-based generative models have emerged as alternatives to generative adversarial networks (GANs) and normalizing flows for tasks involving learning and sampling from complex image distributions. In this work we investigate the ability of these models to generate fields in two astrophysical contexts: dark matter mass density fields from cosmological simulations and images of interstellar dust. We examine the fidelity of the sampled cosmological fields relative to the true fields using three different metrics, and identify potential issues to address. We demonstrate a proof-of-concept application of the model trained on dust in denoising dust images. To our knowledge, this is the first application of this class of models to the interstellar medium.