Learning to Denoise Astronomical Images with U-nets

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.

References in corpus (11)

• Cosmic-Ray Rejection by Laplacian Edge Detection
• Multi-Scale Context Aggregation by Dilated Convolutions
• A guide to convolution arithmetic for deep learning
• Searching for Activation Functions
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• Machine Learning in Astronomy: a practical overview
• Fast cosmic web simulations with generative adversarial networks
• ExoGAN: Retrieving Exoplanetary Atmospheres Using Deep Convolutional Generative Adversarial Networks
• How to coadd images? I. Optimal source detection and photometry using ensembles of images
• How to coadd images? II. A coaddition image that is optimal for any purpose in the background dominated noise limit
• Astronomical Image Denoising Using Dictionary Learning

Cited by in corpus (19)

• The DAWES review 10: The impact of deep learning for the analysis of galaxy surveys
• Deep Learning-Based Super-Resolution and De-Noising for XMM-Newton Images
• Deep Learning for Optical Tweezers
• Encoding large scale cosmological structure with Generative Adversarial Networks
• Prospects for future studies using deep imaging: Analysis of individual Galactic cirrus filaments
• Super-resolving Herschel imaging: a proof of concept using Deep Neural Networks
• The problem of dust attenuation in photometric decomposition of edge-on galaxies and possible solutions
• Painting baryons onto N-body simulations of galaxy clusters with image-to-image deep learning
• Astronomical image denoising by self-supervised deep learning and restoration processes
• MaLeFiSenta: Machine Learning for FilamentS Identification and orientation in the ISM
• Noise reduction on single-shot images using an autoencoder
• Galaxy Spectra Networks (GaSNet). III. Generative pre-trained network for spectrum reconstruction, redshift estimate and anomaly detection
• Noise2Astro: Astronomical Image Denoising With Self-Supervised NeuralNetworks
• A morphological segmentation approach to determining bar lengths
• A Machine Learning Approach to Enhancing eROSITA Observations
• Deeper detection limits in astronomical imaging using self-supervised spatiotemporal denoising
• Efficient neutral-IGM inference from noisy 21-cm forest spectra with latent-space U-Net encoding and XGBoost
• ST-FL: Style Transfer Preprocessing in Federated Learning for COVID-19 Segmentation
• A CNN--Transformer Denoiser for low-$S/N$ Galaxy Spectra: Stellar Population Recovery in Synthetic Tests