E-Print Archive

There are 4282 abstracts currently viewable.


Advanced Search
Main Page Add New E-Print Submitter
News Help/FAQ About Preferences
Manage Key Phrase
* News 04/04/20 * The archive is using a new backend database. This has thrown up a few SQL errors in the last few days. If you have any issues please email adavey@nso.edu with either the number of eprint you are trying to edit or a link to your preprint.

Image Quality Assessment for Full-Disk Solar Observations with Generative Adversarial Networks View all abstracts by submitter

Robert Jarolim   Submitted: 2020-08-28 01:05

Within the last decades, solar physics has entered the era of big data and the amount of data being constantly produced from ground- and space-based observatories can no longer be purely analyzed by human observers. In order to assure a stable series of recorded images of sufficient quality for further scientific analysis, an objective image quality measure is required. Especially when dealing with ground-based observations, which are subject to varying seeing conditions and clouds, the quality assessment has to take multiple effects into account and provide information about the affected regions. The automatic and robust identification of quality-degrading effects is a critical task, in order to maximize the scientific return from the observations and to allow for event detections in real-time. In this study, we develop a deep learning method that is suited to identify anomalies and provide an image quality assessment of solar full-disk Hα filtergrams. The approach is based on the structural appearance and the true image distribution of high-quality observations. We employ a neural network with an encoder-decoder architecture to perform an identity transformation of selected high-quality observations. The encoder network is used to achieve a compressed representation of the input data, which is reconstructed to the original by the decoder. We use adversarial training to recover truncated information based on the high-quality image distribution. When images with reduced quality are transformed, the reconstruction of unknown features (e.g., clouds, contrails, partial occultation) shows deviations from the original. This difference is used to quantify the quality of the observations and to identify the affected regions. In addition, we present an extension of this architecture by using also low-quality samples in the training step, which takes the characteristics of both quality domains into account and improves the sensitivity for minor image quality degradation. We apply our method to full-disk Hα filtergrams from Kanzelhöhe Observatory recorded during 2012-2019 and demonstrate its capability to perform a reliable image quality assessment for various atmospheric conditions and instrumental effects. Our quality metric achieves an accuracy of 98.5% in distinguishing observations with quality-degrading effects from clear observations and provides a continuous quality measure which is in good agreement with the human perception. The developed method is capable of providing a reliable image quality assessment in real-time, without the requirement of reference observations. Our approach has the potential for further application to similar astrophysical observations and requires only little effort of manual labeling.

Authors: R. Jarolim, A. M. Veronig, W. Pötzi, T. Podladchikova
Projects: None

Publication Status: accepted
Last Modified: 2020-09-01 16:40
Go to main E-Print page  Time Series Analysis of Photospheric Magnetic Parameters of Flare-quiet versus Flaring Active Regions: Scaling Properties of Fluctuations  Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning  Edit Entry  Download Preprint  Delete Entry 

Go to main E-Print pageGo to main E-Print page.
Previous AbstractPrevious Abstract.
Next AbstractNext Abstract.
Download PreprintDownload Preprint.
Submitter's HomepageSubmitters Homepage.
Edit EntryEdit Entry.
View All Abstracts By SubmitterView all abstracts by submitter.
Delete AbstractDelete abstract.

Latest Entries
Propagation Effects in Quiet Sun Observations at Meter Wavelengths
Twin Null-Point-Associated Major Eruptive Three-Ribbon Flares with Unusual Microwave Spectra
Trajectory Determination for Coronal Ejecta Observed by WISPR/Parker Solar Probe
Recurring Homologous Solar Eruptions in NOAA AR 11429
Resonant absorption: transformation of compressive motions into vortical motion
The depth and the vertical extent of the energy deposition layer in a medium-class solar flare
Helicity proxies from linear polarisation of solar active regions
The Submillimeter Active Region Excess Brightness Temperature during Solar Cycles 23 and 24
Nanoflare Diagnostics from Magnetohydrodynamic Heating Profiles
The Solar Orbiter mission - Science Overview
Time Series Analysis of Photospheric Magnetic Parameters of Flare-quiet versus Flaring Active Regions: Scaling Properties of Fluctuations
Image Quality Assessment for Full-Disk Solar Observations with Generative Adversarial Networks
Identifying and Tracking Solar Magnetic Flux Elements with Deep Learning
Active Region Irradiance During Quiescent Periods: New Insights from Sun-as-a-star Spectra
Probing solar flare accelerated electron distributions with prospective X-ray polarimetry missions
Accelerating and Supersonic Density Fluctuations in Coronal Hole Plumes: Signature of Nascent Solar Winds
Sequential Lid Removal in a Triple-Decker Chain of CME-Producing Solar Eruptions
RESIK and RHESSI observations of the 20 September 2002 flare
Starspot mapping with adaptive parallel tempering I: Implementation of computational code
Heating and Eruption of a Solar Circular Ribbon Flare

Related Pages
MSU Solar Physics.
Max Millennium Science Mail Archive.
Max Millennium Message of the Day Mail Archive.
Max Millennium Flare Catalog

Archive Maintainer
Alisdair Davey

© 2000-2020 Solar Physics Group - Montana State University