Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations

2025/09/21 by Chalmers, Alexis, Azim Ahmadzadeh, Ahmadzadeh, Azim
Biochemistry, Genetics and Molecular Biology · Materials Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Chemical and Physical Properties of Materials #FOS: Computer and information sciences #FOS: Physical sciences #Geomagnetism and Paleomagnetism Studies #Solar and Space Plasma Dynamics #Solar and Stellar Astrophysics (astro-ph.SR)

paper · pdf · doi:10.48550/arxiv.2509.18214

openalex publication_date 2025/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Dataset of example filament cutouts for use in demo notebook. Filaments were extracted from GONG H-Alpha solar observations based on annotations from the MAGFiLO dataset. Of the extracted filaments 102 cutouts, 34 of each class, were selected to create a dataset of examples.

Citations

• Developing an Automated Detection, Tracking and Analysis Method for Solar Filaments Observed by CHASE via Machine Learning
• A ConvNet for the 2020s
• A ConvNet for the 2020s
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Toward Filament Segmentation Using Deep Neural Networks
• Axiomatic Attribution for Deep Networks
• Wide Residual Networks
• Deep Residual Learning for Image Recognition
• Microsoft COCO: Common Objects in Context

Related

• Machine learning for reconstruction of polarity inversion lines from solar filaments
• Solar Filament Physiognomy: Inferring Magnetic Quantities from Imaging Observations
• Properties of filament in Solar cycle 20-23 from McIntosh database
• EdgeAttNet: Towards Barb-Aware Filament Segmentation
• A Modern ConvNet for Solar Filament Detection