Learning to Denoise Astronomical Images with U-nets

TL;DR

This paper introduces Astro U-net, a neural network that effectively denoises and enhances astronomical images, significantly improving signal-to-noise ratio and star recovery, thus reducing telescope time for deep space observations.

Contribution

The paper presents a novel convolutional neural network architecture, Astro U-net, specifically designed for astronomical image denoising and enhancement, demonstrating superior performance on Hubble Space Telescope data.

Findings

Achieves noise reduction equivalent to doubling exposure time.

Recovers 95.9% of stars with 2.26% flux error.

Increases signal-to-noise ratio by 1.63 times, reducing required telescope time.

Abstract

Astronomical images are essential for exploring and understanding the universe. Optical telescopes capable of deep observations, such as the Hubble Space Telescope, are heavily oversubscribed in the Astronomical Community. Images also often contain additive noise, which makes de-noising a mandatory step in post-processing the data before further data analysis. In order to maximise the efficiency and information gain in the post-processing of astronomical imaging, we turn to machine learning. We propose Astro U-net, a convolutional neural network for image de-noising and enhancement. For a proof-of-concept, we use Hubble space telescope images from WFC3 instrument UVIS with F555W and F606W filters. Our network is able to produce images with noise characteristics as if they are obtained with twice the exposure time, and with minimum bias or information loss. From these images, we are able to recover 95.9% of stars with an average flux error of 2.26%. Furthermore the images have, on average, 1.63 times higher signal-to-noise ratio than the input noisy images, equivalent to the stacking of at least 3 input images, which means a significant reduction in the telescope time needed for future astronomical imaging campaigns.