The CHASM-SWPC Dataset for Coronal Hole Detection & Analysis

2025-11-17

AI Summary

To address the low accuracy and high annotation cost of automated coronal hole (CH) detection, this paper proposes CHASM, a semi-automatic annotation framework that efficiently converts SWPC manual daily synoptic maps into high-quality, pixel-level segmentation masks. This yields CHASM-SWPC-1111—the first large-scale, long-term (1996–2023) CH dataset comprising 1,111 annotated images. Furthermore, we design CHRONNOS, a multi-spectral neural network that jointly fuses SDO/AIA extreme ultraviolet (EUV) images across multiple wavelengths with prior manual CH maps for end-to-end training. On a standardized test set, CHRONNOS achieves an accuracy of 0.9805, a True Skill Statistic (TSS) of 0.6807, and an Intersection-over-Union (IoU) of 0.5668—substantially outperforming existing pre-trained methods. This work delivers three core contributions: (1) a high-quality, long-term benchmark CH dataset; (2) an efficient semi-automatic annotation tool; and (3) an advanced multi-spectral deep learning architecture for CH identification.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Coronal holes (CHs) are low-activity, low-density solar coronal regions with open magnetic field lines (Cranmer 2009). In the extreme ultraviolet (EUV) spectrum, CHs appear as dark patches. Using daily hand-drawn maps from the Space Weather Prediction Center (SWPC), we developed a semi-automated pipeline to digitize the SWPC maps into binary segmentation masks. The resulting masks constitute the CHASM-SWPC dataset, a high-quality dataset to train and test automated CH detection models, which is released with this paper. We developed CHASM (Coronal Hole Annotation using Semi-automatic Methods), a software tool for semi-automatic annotation that enables users to rapidly and accurately annotate SWPC maps. The CHASM tool enabled us to annotate 1,111 CH masks, comprising the CHASM-SWPC-1111 dataset. We then trained multiple CHRONNOS (Coronal Hole RecOgnition Neural Network Over multi-Spectral-data) architecture (Jarolim et al. 2021) neural networks using the CHASM-SWPC dataset and compared their performance. Training the CHRONNOS neural network on these data achieved an accuracy of 0.9805, a True Skill Statistic (TSS) of 0.6807, and an intersection-over-union (IoU) of 0.5668, which is higher than the original pretrained CHRONNOS model Jarolim et al. (2021) achieved an accuracy of 0.9708, a TSS of 0.6749, and an IoU of 0.4805, when evaluated on the CHASM-SWPC-1111 test set.

Problem

• Developing semi-automated pipeline for coronal hole digitization
• Creating high-quality dataset for automated CH detection models
• Training neural networks to improve coronal hole recognition accuracy

Innovation

• Semi-automated pipeline digitizes hand-drawn solar maps
• CHASM tool enables rapid annotation of coronal holes
• CHRONNOS neural network trained achieves higher accuracy