Multi-channel coronal hole detection with convolutional neural networks

Abstract

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. We use a convolutional neural network to identify the boundaries of coronal holes from the seven EUV channels of the Atmospheric Imaging Assembly (AIA) as well as from line-of-sight magnetograms from the Helioseismic and Magnetic Imager (HMI) onboard 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 relations across the full solar-disk into account. 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 $>1.5\cdot 10^{10}$ km${}^2$ identified during the time range 11/2010 - 12/2016, 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 the direct comparison over short time scales 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 be also obtained solely from line-of-sight magnetograms.

References in corpus (23)

• A Comparison of Flare Forecasting Methods, I: Results from the "All-Clear" Workshop
• Automated Coronal Hole Detection using Local Intensity Thresholding Techniques
• Photometric and Thermal Cross-calibration of Solar EUV Instruments
• A Machine Learning Dataset Prepared From the NASA Solar Dynamics Observatory Mission
• Statistical Analysis and Catalog of Non-polar Coronal Holes Covering the SDO-era using CATCH
• Solar wind prediction using deep learning
• Automated Coronal Hole Identification via Multi-Thermal Intensity Segmentation
• Characteristics of Low-Latitude Coronal Holes near the Maximum of Solar cycle 24
• Segmentation of coronal holes in solar disk images with a convolutional neural network
• Measurements of EUV Coronal Holes and Open Magnetic Flux
• Reconstructing coronal hole areas with EUHFORIA and adapted WSA model: optimising the model parameters
• Fast Solar Image Classification Using Deep Learning and its Importance for Automation in Solar Physics
• Photospheric magnetic structure of coronal holes
• The Dependence of the Peak Velocity of High-Speed Solar Wind Streams as Measured in the Ecliptic by ACE and the STEREO satellites on the Area and Co-Latitude of their Solar Source Coronal Holes
• Solar Coronal Magnetic Field Extrapolation from Synchronic Data with AI-generated Farside
• Solar image denoising with convolutional neural networks
• Automated identification of coronal holes from synoptic EUV maps
• A statistical study of long-term evolution of coronal hole properties as observed by SDO
• Differential Emission Measure Plasma Diagnostics of a Long-Lived Coronal Hole
• The Observational Uncertainty of Coronal Hole Boundaries in Automated Detection Schemes
• Statistical Approach on Differential EmissionMeasure of Coronal Holes using the CATCH Catalog
• Machine-learning approach to identification of coronal holes in solar disk images and synoptic maps
• Image Quality Assessment for Full-Disk Solar Observations with Generative Adversarial Networks

Cited by in corpus (9)

• A Universal Method for Solar Filament Detection from H-alpha Observations using Semi-supervised Deep Learning
• SCSS-Net: Solar Corona Structures Segmentation by Deep Learning
• Instrument-To-Instrument translation: Instrumental advances drive restoration of solar observation series via deep learning
• SuNeRF: 3D reconstruction of the solar EUV corona using Neural Radiance Fields
• Quantifying the Consistency and Characterizing the Confidence of Coronal Holes Detected by Active Contours without Edges (ACWE)
• Magnetic Field-Constrained Ensemble Image Segmentation of Coronal Holes in Chromospheric Observations
• Automatic detection of Ellerman bombs using Deep Learning
• Siberian radioheliograph image classification using ensemble of CLIP, EfficientNet and CatBoost models
• Identification of Coronal Holes on AIA/SDO images using unsupervised Machine Learning