E-Print Archive

There are 4396 abstracts currently viewable.


Advanced Search
Main Page Add New E-Print Submitter
News Help/FAQ About Preferences
Manage Key Phrase
Multi-channel coronal hole detection with convolutional neural networks View all abstracts by submitter

Robert Jarolim   Submitted: 2021-05-31 02:31

Context. A precise detection of the coronal hole boundary is of primary interest for a better understanding of the physics of coronal holes, their role in the solar cycle evolution, and space weather forecasting. Aims. We develop a reliable, fully automatic method for the detection of coronal holes that provides consistent full-disk segmentation maps over the full solar cycle and can perform in real-time. Methods. We use a convolutional neural network to identify the boundaries of coronal holes from the seven extreme ultraviolet (EUV) channels of the Atmospheric Imaging Assembly (AIA) and from the line-of-sight magnetograms provided by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO). For our primary model (Coronal Hole RecOgnition Neural Network Over multi-Spectral-data; CHRONNOS) we use a progressively growing network approach that allows for efficient training, provides detailed segmentation maps, and takes into account relations across the full solar disk. Results. We provide a thorough evaluation for performance, reliability, and consistency by comparing the model results to an independent manually curated test set. Our model shows good agreement to the manual labels with an intersection-over-union (IoU) of 0.63. From the total of 261 coronal holes with an area > 1.5e10 km2 identified during the time-period from November 2010 to December 2016, 98.1% were correctly detected by our model. The evaluation over almost the full solar cycle no. 24 shows that our model provides reliable coronal hole detections independent of the level of solar activity. From a direct comparison over short timescales of days to weeks, we find that our model exceeds human performance in terms of consistency and reliability. In addition, we train our model to identify coronal holes from each channel separately and show that the neural network provides the best performance with the combined channel information, but that coronal hole segmentation maps can also be obtained from line-of-sight magnetograms alone. Conclusions. The proposed neural network provides a reliable data set for the study of solar-cycle dependencies and coronal-hole parameters. Given the fast and robust coronal hole segmentation, the algorithm is also highly suitable for real-time space weather applications.

Authors: R. Jarolim, A.M. Veronig, S. Hofmeister, S.G. Heinemann, M. Temmer, T. Podladchikova, K. Dissauer
Projects: SDO-AIA

Publication Status: accepted
Last Modified: 2021-05-31 11:55
Go to main E-Print page  Fast magnetoacoustic wave trains: from tadpoles to boomerangs  FOXSI-2 Solar Microflares. II. Hard X-ray Imaging Spectroscopy and Flare Energetics  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
The Solar Memory From Hours to Decades
Solar chromosphere heating and generation of plasma outflows by impulsively generated two-fluid Alfvén waves
Radio evidence for a shock wave reflected by a coronal hole
Hemispheric sunspot numbers 1874 - 2020
Temperature in Solar Sources of 3He-rich Solar Energetic Particles and Relation to Ion Abundances
The long period of 3He-rich solar energetic particles measured by Solar Orbiter 2020 November 1723
Tracing Hα Fibrils through Bayesian Deep Learning
Energetics and 3-D Structure of Elementary Events in Solar Coronal Heating
Forecasting the Remaining Duration of an Ongoing Solar Flare
A fundamental mechanism of solar eruption initiation
Thermal Trigger for Solar Flares III: Effect of the Oblique Layer Fragmentation
Measurements of Coronal Magnetic Field Strengths in Solar Active Region Loops
Characteristic time of stellar flares on Sun-like stars
M-dwarf's Chromosphere, Corona and Wind Connection via the Nonlinear Alfvén Wave
Bayesian evidence for a nonlinear damping model for coronal loop oscillations
Small-scale Turbulent Motion of the Plasma in a Solar Filament as the Precursor of Eruption
Validation of the PDFI_SS method for electric field inversions using a magnetic flux emergence simulation
Investigation on the Spatiotemporal Structures of Supra-Arcade Spikes
Magnetic helicity and energy budget around large confined and eruptive solar flares
One dimensional prominence threads: I. Equilibrium models

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