A Modern ConvNet for Solar Filament Detection

2026-07-27

AI Summary

This study addresses the challenges of automatic solar filament detection, including difficulties in multi-scale feature extraction, long-tailed data distributions, and scarcity of annotated samples. To tackle these issues, the authors propose an end-to-end detection pipeline: they first construct a small-scale manually annotated MHAS dataset, then develop MORDEN—a semantic segmentation model specifically designed for multi-scale feature fusion—followed by DenseCRF for edge refinement and DBSCAN clustering for post-processing. This integrated approach yields AHAS, the first high-quality large-scale solar filament dataset. Experimental results demonstrate that MORDEN outperforms existing public models, and the overall pipeline significantly enhances detection accuracy and reliability.

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.

Problem

• solar filament detection
• semantic segmentation
• multiscale feature extraction
• long-tail distribution
• large-scale dataset

Innovation

• MORDEN
• multiscale feature extraction
• solar filament detection
• semantic segmentation
• DenseCRF