English

HIDM: Emulating Large Scale HI Maps using Score-based Diffusion Models

Cosmology and Nongalactic Astrophysics 2023-11-03 v1 Instrumentation and Methods for Astrophysics

Abstract

Efficiently analyzing maps from upcoming large-scale surveys requires gaining direct access to a high-dimensional likelihood and generating large-scale fields with high fidelity, which both represent major challenges. Using CAMELS simulations, we employ the state-of-the-art score-based diffusion models to simultaneously achieve both tasks. We show that our model, HIDM, is able to efficiently generate high fidelity large scale HI maps that are in a good agreement with the CAMELS's power spectrum, probability distribution, and likelihood up to second moments. HIDM represents a step forward towards maximizing the scientific return of future large scale surveys.

Keywords

Cite

@article{arxiv.2311.00833,
  title  = {HIDM: Emulating Large Scale HI Maps using Score-based Diffusion Models},
  author = {Sultan Hassan and Sambatra Andrianomena},
  journal= {arXiv preprint arXiv:2311.00833},
  year   = {2023}
}

Comments

Accepted to Machine Learning and the Physical Sciences Workshop, NeurIPS 2023