Segmentation of coronal holes in solar disk images with a convolutional neural network

Abstract

Current coronal holes segmentation methods typically rely on image thresholding and require non-trivial image pre- and post-processing. We have trained a neural network that accurately isolates CHs from SDO/AIA 193 Angstrom solar disk images without additional complicated steps. We compare results with publicly available catalogues of CHs and demonstrate stability of the neural network approach. In our opinion, this approach can outperform hand-engineered solar image analysis and will have a wide application to solar data. In particular, we investigate long-term variations of CH indices within the solar cycle 24 and observe increasing of CH areas in about three times from minimal values in the maximum of the solar cycle to maximal values during the declining phase of the solar cycle.

References in corpus (9)

• A guide to convolution arithmetic for deep learning
• Revisiting the Sunspot Number
• Automated Coronal Hole Detection using Local Intensity Thresholding Techniques
• DeepVel: deep learning for the estimation of horizontal velocities at the solar surface
• Enhancing SDO/HMI images using deep learning
• Automated Coronal Hole Identification via Multi-Thermal Intensity Segmentation
• Real-time solar wind prediction based on SDO/AIA coronal hole data
• Solar Wind Forecasting with Coronal Holes
• Parameters of the Magnetic Flux inside Coronal Holes

Cited by in corpus (15)

• Statistical Analysis and Catalog of Non-polar Coronal Holes Covering the SDO-era using CATCH
• Stokes Inversion based on Convolutional Neural Networks
• Solar Coronal Magnetic Field Extrapolation from Synchronic Data with AI-generated Farside
• Solar image denoising with convolutional neural networks
• Multi-channel coronal hole detection with convolutional neural networks
• The Observational Uncertainty of Coronal Hole Boundaries in Automated Detection Schemes
• Probabilistic prediction of Dst storms one-day-ahead using Full-Disk SoHO Images
• Machine-learning approach to identification of coronal holes in solar disk images and synoptic maps
• SCSS-Net: Solar Corona Structures Segmentation by Deep Learning
• Automatic detection of Ellerman bombs using Deep Learning
• Magnetic Field-Constrained Ensemble Image Segmentation of Coronal Holes in Chromospheric Observations
• Deep solar ALMA neural network estimator for image refinement and estimates of small-scale dynamics
• Earth-affecting Solar Transients: A Review of Progresses in Solar Cycle 24
• Siberian radioheliograph image classification using ensemble of CLIP, EfficientNet and CatBoost models
• Identification of Coronal Holes on AIA/SDO images using unsupervised Machine Learning