Application and interpretation of deep learning for identifying pre-emergence magnetic-field patterns

Abstract

Magnetic flux generated within the solar interior emerges to the surface, forming active regions (ARs) and sunspots. Flux emergence may trigger explosive events, such as flares and coronal mass ejections and therefore understanding emergence is useful for space-weather forecasting. Evidence of any pre-emergence signatures will also shed light on sub-surface processes responsible for emergence. In this paper, we present a first analysis of emerging ARs from the Solar Dynamics Observatory/Helioseismic Emerging Active Regions (SDO/HEAR) dataset (Schunker et al. 2016) using deep convolutional neural networks (CNN) to characterize pre-emergence surface magnetic-field properties. The trained CNN classifies between pre-emergence (PE) line-of-sight magnetograms and a control set of non-emergence (NE) magnetograms with a True Skill Statistic (TSS) score of ~85%, 3h prior to emergence and ~40\%, 24h prior to emergence. Our results are better than a baseline classification TSS obtained using discriminant analysis of only the unsigned magnetic flux. We develop a network pruning algorithm to interpret the trained CNN and show that the CNN incorporates filters that respond positively as well as negatively to the unsigned magnetic flux of the magnetograms. Using synthetic magnetograms, we demonstrate that the CNN output is sensitive to the length-scale of the magnetic regions with small-scale and intense fields producing maximum CNN output and possibly a characteristic pre-emergence pattern. Given increasing popularity of deep learning, techniques developed here for interpretation of the trained CNN -- using network pruning and synthetic data -- are relevant for future applications in solar and astrophysical data analysis.

arXiv comment24 pages, 24 figures, accepted for publication in ApJ

References in corpus (11)

• The Helioseismic and Magnetic Imager (HMI) Vector Magnetic Field Pipeline: SHARPs -- Space-weather HMI Active Region Patches
• The case for a distributed solar dynamo shaped by near-surface shear
• Solar Flare Prediction Using SDO/HMI Vector Magnetic Field Data with a Machine-Learning Algorithm
• The Global Solar Dynamo
• Helioseismology of Pre-Emerging Active Regions II: Average Emergence Properties
• Mean-field and direct numerical simulations of magnetic flux concentrations from vertical field
• SDO/HMI survey of emerging active regions for helioseismology
• Helioseismology of Pre-Emerging Active Regions I: Overview, Data, and Target Selection Criteria
• Helioseismology of Pre-Emerging Active Regions III: Statistical Analysis
• Average motion of emerging solar active region polarities I: Two phases of emergence
• The Properties of the Tilts of Bipolar Solar Regions

Cited by in corpus (2)

• A Search for Monochromatic Light Toward the Galactic Centre
• Evolution of the magnetic field and flows of solar active regions with persistent magnetic bipoles before emergence