Enhancing SDO/HMI images using deep learning

Abstract

The Helioseismic and Magnetic Imager (HMI) provides continuum images and magnetograms with a cadence better than one per minute. It has been continuously observing the Sun 24 hours a day for the past 7 years. The obvious trade-off between full disk observations and spatial resolution makes HMI not enough to analyze the smallest-scale events in the solar atmosphere. Our aim is to develop a new method to enhance HMI data, simultaneously deconvolving and super-resolving images and magnetograms. The resulting images will mimic observations with a diffraction-limited telescope twice the diameter of HMI. Our method, which we call Enhance, is based on two deep fully convolutional neural networks that input patches of HMI observations and output deconvolved and super-resolved data. The neural networks are trained on synthetic data obtained from simulations of the emergence of solar active regions. We have obtained deconvolved and supper-resolved HMI images. To solve this ill-defined problem with infinite solutions we have used a neural network approach to add prior information from the simulations. We test Enhance against Hinode data that has been degraded to a 28 cm diameter telescope showing very good consistency. The code is open source.

13 pages, 10 figures. Accepted for publication in Astronomy & Astrophysics

References in corpus (12)

• Deep Learning in Neural Networks: An Overview
• The Solar Optical Telescope for the Hinode Mission: An Overview
• Generative Adversarial Networks recover features in astrophysical images of galaxies beyond the deconvolution limit
• The Open Flux Problem
• The intensity contrast of solar granulation: comparing Hinode SP results with MHD simulations
• On the Formation of Active Regions
• DeepVel: deep learning for the estimation of horizontal velocities at the solar surface
• Sparse inversion of Stokes profiles. I. Two-dimensional Milne-Eddington inversions
• Comparison of Ground- and Space-based Longitudinal Magnetograms
• Spatial deconvolution of spectropolarimetric data: an application to quiet Sun magnetic elements
• Zeeman-Tomography of the Solar Photosphere -- 3-Dimensional Surface Structures Retrieved from Hinode Observations
• Comparison between Hinode/SOT and SDO/HMI, AIA Data for the Study of the Solar Flare Trigger Process

Cited by in corpus (23)

• 2022 Review of Data-Driven Plasma Science
• Stokes Inversion based on Convolutional Neural Networks
• Real-time multiframe blind deconvolution of solar images
• Segmentation of coronal holes in solar disk images with a convolutional neural network
• Detection of the strongest magnetic field in a sunspot light bridge
• Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics
• Solar image denoising with convolutional neural networks
• Mimicking spectropolarimetric inversions using convolutional neural networks
• Center-to-limb variation of spectral lines and continua observed with SST/CRISP and SST/CHROMIS
• Solar Image Restoration with the Cycle-GAN Based on Multi-Fractal Properties of Texture Features
• Heating of the solar chromosphere through current dissipation
• Automating Ellerman bomb detection in ultraviolet continua
• ALMA observations of transient heating in a solar active region
• Probabilistic prediction of Dst storms one-day-ahead using Full-Disk SoHO Images
• Exploring the Limits of Synthetic Creation of Solar EUV Images via Image-to-Image Translation
• Instrument-To-Instrument translation: Instrumental advances drive restoration of solar observation series via deep learning
• Background-subtracted Solar Activity Maps
• Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): I. Overview, Magnetohydrodynamic Modeling, and Stokes Profile Synthesis
• Morphological evidence for nanoflares heating warm loops in the solar corona
• A nonlinear solar magnetic field calibration method for the filter-based magnetograph by the residual network
• Mapping the Sun's upper photosphere with artificial neural networks
• Enhancing Image Resolution of Solar Magnetograms: A Latent Diffusion Model Approach
• Deep solar ALMA neural network estimator for image refinement and estimates of small-scale dynamics