Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

POP-CORN: Validation of a new coronal hole detection tool based on neural networks

K. H. P. Henadhira Arachchige, B. Perri, A. S. Brun

Abstract

The properties and spatial distribution of large-scale structures of the solar corona determine the observed solar wind structure at 1 au. Coronal holes are a major source of fast solar wind, an important geo-effective component, and appear as large dark patches in extreme ultraviolet images. Solar observatories provide images of the solar corona at different wavelengths, enabling identification of coronal hole morphology and other large-scale structures along a given line of sight. The problem is that although models exist, few work in real time, separate coronal holes from other dark features, or are fully automatic and suitable for comparison with models. The main goal of this work is to develop an automatic threshold-based coronal hole detection tool across solar cycles 23, 24, and 25 using artificial intelligence. The only user input is the date, enabling retrieval of the threshold value used to detect coronal hole contours in line-of-sight extreme ultraviolet images from SDO/AIA and SoHO/EIT. We retrieve data affecting the threshold due to contrast changes from the Heliophysics Events Knowledge database for large-scale features such as active regions, solar flares, coronal mass ejections, and filaments, and engineer them to train the neural network model (POP-CORN). The model input comprises categorical features of large-scale structures in the solar corona, including spatial distribution and properties such as solar flare class by intensity. The neural network model is trained to achieve higher accuracy and determines the threshold needed to detect coronal holes, allowing their boundaries to be identified automatically and consistently. We conclude that properties of large-scale structures affect the determination of coronal hole regions, and incorporating these properties into training improves detection.

POP-CORN: Validation of a new coronal hole detection tool based on neural networks

Abstract

The properties and spatial distribution of large-scale structures of the solar corona determine the observed solar wind structure at 1 au. Coronal holes are a major source of fast solar wind, an important geo-effective component, and appear as large dark patches in extreme ultraviolet images. Solar observatories provide images of the solar corona at different wavelengths, enabling identification of coronal hole morphology and other large-scale structures along a given line of sight. The problem is that although models exist, few work in real time, separate coronal holes from other dark features, or are fully automatic and suitable for comparison with models. The main goal of this work is to develop an automatic threshold-based coronal hole detection tool across solar cycles 23, 24, and 25 using artificial intelligence. The only user input is the date, enabling retrieval of the threshold value used to detect coronal hole contours in line-of-sight extreme ultraviolet images from SDO/AIA and SoHO/EIT. We retrieve data affecting the threshold due to contrast changes from the Heliophysics Events Knowledge database for large-scale features such as active regions, solar flares, coronal mass ejections, and filaments, and engineer them to train the neural network model (POP-CORN). The model input comprises categorical features of large-scale structures in the solar corona, including spatial distribution and properties such as solar flare class by intensity. The neural network model is trained to achieve higher accuracy and determines the threshold needed to detect coronal holes, allowing their boundaries to be identified automatically and consistently. We conclude that properties of large-scale structures affect the determination of coronal hole regions, and incorporating these properties into training improves detection.

Paper Structure

This paper contains 28 sections, 7 equations, 13 figures, 3 tables.

Table of Contents

  1. Introduction
  2. AI Model
  3. Identifying the Coronal Hole boundaries
  4. Relation between the threshold values in SDO & SOHO
  5. Feature engineering
  6. Neural Network (NN) Model (POP-CORN)
  7. Model Validation
  8. Results
  9. Solar Cycle 25
  10. Solar Cycle 24
  11. Solar Cycle 23
  12. Discussion
  13. Conclusions
  14. Additional Figures
  15. Hotelling’s $T^{2}$ Test
  16. ...and 13 more sections

Figures (13)

  • Figure 1: EUV images of the Sun from SDO/AIA for the time period of 2021:02:15 for the wavelengths 171Å, 193Å, 211Å, and for the composite image.
  • Figure 2: Comparison for threshold value from our image processing technique (left) and from the EZSEG algorithm (right) for the date 2018-01-15 00:00:16.84 for SDO/AIA 193$\AA$.
  • Figure 3: Illustration of the relationship between SDO/AIA 193$\AA$ (left) and SOHO/EIT $195\AA$ (right) threshold values for 2010-06-23 00:00:06.601024 X 1024 resolution.
  • Figure 4: Figure showing the correlation between predicted data and true values. The red line denotes the fitted linear regression model.
  • Figure 5: Figure showing overlaid histograms of predicted and true values. The Wasserstein distance quantifies the difference between the two distributions.
  • ...and 8 more figures