Automatic Classification of Magnetic Chirality of Solar Filaments from H-Alpha Observations
This work addresses the need for reliable chirality classification in solar physics, which is incremental as it builds on existing image classification methods applied to a new, larger dataset.
The study tackled the problem of classifying the magnetic chirality of solar filaments from H-Alpha observations by establishing a reproducible baseline on the MAGFiLO dataset, achieving per-class accuracies of 0.69 for left chirality and 0.73 for right chirality using a ConvNeXtBase model.
In this study, we classify the magnetic chirality of solar filaments from H-Alpha observations using state-of-the-art image classification models. We establish the first reproducible baseline for solar filament chirality classification on the MAGFiLO dataset. The MAGFiLO dataset contains over 10,000 manually-annotated filaments from GONG H-Alpha observations, making it the largest dataset for filament detection and classification to date. Prior studies relied on much smaller datasets, which limited their generalizability and comparability. We fine-tuned several pre-trained, image classification architectures, including ResNet, WideResNet, ResNeXt, and ConvNeXt, and also applied data augmentation and per-class loss weights to optimize the models. Our best model, ConvNeXtBase, achieves a per-class accuracy of 0.69 for left chirality filaments and $0.73$ for right chirality filaments.