A Modern ConvNet for Solar Filament Detection
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method to automatically find solar filaments, which are structures on the Sun, using deep learning. They created a small detailed dataset and a special model called MORDEN that looks at different sizes of features to better detect these filaments. They also used post-processing techniques like DenseCRF and DBSCAN to refine the results. Their method produced a larger dataset and showed better performance compared to other existing models. This work helps improve the use of AI for studying solar filaments.
Solar filamentDeep learningSemantic segmentationMultiscale feature extractionH-alpha spectraDense Conditional Random Field (DenseCRF)DBSCANDataset annotationPost-processing
Authors
J. R. Hu, Q. Hao, Z. Zheng, P. F. Chen, C. Li, Y. Meng
Abstract
Automated solar filament detection using deep learning faces several challenges. Semantic segmentation of solar filaments is a complicated multiscale feature extraction task with long-tail distribution. Furthermore, a large-scale, highly complete, and finely detailed dataset has become mandatory for providing abundant information. To address these challenges, we present a series of machine learning approaches to develop a solar filament detection workflow that performs superbly. First, we manually annotated a small-scale solar filament dataset based on H$α$ spectra called MHAS. Next, we developed the Multiscale ORiented DENdritic (MORDEN) model, a semantic segmentation model focusing on multiscale feature extraction. We also introduced the Dense Conditional Random Field (DenseCRF) and Density-Based Spatial Clustering of Applications with Noise (DBSCAN) methods for post-processing. Using the proposed workflow, we generated a large-scale, high-quality dataset called AHAS. Experimental results demonstrate that MORDEN outperforms several existing solar filament semantic segmentation models with open access. DenseCRF has been demonstrated to effectively capture fine edge details. We also evaluated the effects of data scaling and the reliability of DBSCAN and found that both approaches yield satisfactory performance. Multiple visualization results substantiate our quantitative findings. Our work provides a foundation for maximizing the potential of deep learning models for solar filament detection.