Comparing Solar Structure Detection Methods in SDO/AIA Observations and the Application to Raw Uncalibrated Data
Open Access
- 23 May 2026
- journal article
- research article
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Machine Learning and Computation
- Vol. 3 (3)
Abstract
Recent advances in solar physics increasingly rely on automated identification of coronal structures using machine learning. Yet most studies emphasize scientific performance without evaluating feasibility for onboard deployment to prioritize downlink observations. This work investigates the automated identification of active regions and coronal holes by applying segmentation and detection techniques to Solar Dynamics Observatory (SDO) data. We compare three approaches: SCSS‐Net, a deep learning model for semantic segmentation; YOLOv8n, a lightweight object detector; and a traditional pipeline based on basic computer vision operations (BCVO). Each method is assessed for its scientific accuracy and its suitability for deployment in future resource‐limited missions. While no direct hardware benchmarking is performed in this study, we assess the feasibility of onboard implementation based on the associated number of trainable parameters, architecture and hardware requirements. Training and evaluation are first conducted on well‐calibrated SDO images. We then extend the evaluation to raw and uncalibrated SDO images affected by instrumental artifacts. Performance is measured using the Intersection over Union (IoU) and Dice score. Results show that while SCSS‐Net achieves the highest segmentation quality, YOLOv8n offers a strong balance between accuracy and efficiency. The BCVO pipeline remains viable under strict hardware limitations. Interestingly, our models retain compatibility on Level‐0 observations. This is the first study comparing these widely used methods from the perspective of onboard deployment. Our findings provide a foundation for designing frameworks tailored to onboard hardware configurations.Keywords
Funding Information
- Horizon 2020 Framework Programme (101082633)
- Belgian Federal Science Policy Office (B2/202/P1/DELPHI)
- HORIZON EUROPE Marie Sklodowska-Curie Actions (101148539)
- Fonds Wetenschappelijk Onderzoek (G0B9923N)
- Fonds Wetenschappelijk Onderzoek (G0B5823N)
- Fonds Wetenschappelijk Onderzoek (G002523N)
- HORIZON EUROPE European Research Council (01095310)
- HORIZON EUROPE European Research Council (101141362)
- KU Leuven (C16/24/010)
- Kyung Hee University (GSX‐20242364)
- Kyung Hee University (GSX‐20253142)
This publication has 37 references indexed in Scilit:
- Convolutional neural network design and evaluation for real-time multivariate time series fault detection in spacecraft attitude sensorsAdvances In Space Research, 2025
- Real-Time Multi-object Tracking Using YOLOv8 and SORT on a SoC FPGA2025
- Optimized k-Nearest neighbors search implementation on resource-constrained FPGA platformsMicroprocessors and Microsystems, 2024
- ResNet 502021
- Coronal Holes Detection Using Supervised Classification2018
- Solar filament eruptions and their physical role in triggering coronal mass ejectionsAdvances In Space Research, 2013
- The Helioseismic and Magnetic Imager (HMI) Investigation for the Solar Dynamics Observatory (SDO)Solar Physics, 2011
- The Atmospheric Imaging Assembly (AIA) on the Solar Dynamics Observatory (SDO)Solar Physics, 2011
- EIT: Extreme-ultraviolet Imaging Telescope for the SOHO missionSolar Physics, 1995
- The SOHO mission: An overviewSolar Physics, 1995