Multi-fidelity Emulator for Cosmological Large Scale 21 cm Lightcone Images: a Few-shot Transfer Learning Approach with GAN

TL;DR

This paper introduces a multi-fidelity GAN-based emulation method that efficiently generates large-scale cosmic reionization lightcone images, significantly reducing computational costs while maintaining high accuracy for upcoming large surveys.

Contribution

The paper presents a novel transfer learning approach using GANs to emulate large-scale cosmological images from small-scale simulations, saving 90% of computational resources.

Findings

High accuracy in lightcone image generation with percentage errors

Achieves 90% reduction in computational resources

Enables efficient large-scale cosmological simulations

Abstract

Large-scale numerical simulations ($\gtrsim 500\rm{Mpc}$) of cosmic reionization are required to match the large survey volume of the upcoming Square Kilometre Array (SKA). We present a multi-fidelity emulation technique for generating large-scale lightcone images of cosmic reionization. We first train generative adversarial networks (GAN) on small-scale simulations and transfer that knowledge to large-scale simulations with hundreds of training images. Our method achieves high accuracy in generating lightcone images, as measured by various statistics with mostly percentage errors. This approach saves computational resources by 90% compared to conventional training methods. Our technique enables efficient and accurate emulation of large-scale images of the Universe.