Composite three-channel preprocessing of SDO/AIA images yields a YOLOv5 prominence detector with mAP@50 of 0.749 and 78% recall that also generalizes to SUVI data.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
astro-ph.SR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
MHD modeling of the 2024 October 26 CME demonstrates that specific pre-eruptive magnetic flux rope footpoint locations and near-real-time background fields are required to reproduce observed complex morphology from multiple viewpoints without fine-tuning.
citing papers explorer
-
A Robust Deep Learning Framework for Prominence Detection through Composite Feature Representations
Composite three-channel preprocessing of SDO/AIA images yields a YOLOv5 prominence detector with mAP@50 of 0.749 and 78% recall that also generalizes to SUVI data.
-
Understanding the complex morphology of a CME II: how pre-eruptive conditions shape CME evolution
MHD modeling of the 2024 October 26 CME demonstrates that specific pre-eruptive magnetic flux rope footpoint locations and near-real-time background fields are required to reproduce observed complex morphology from multiple viewpoints without fine-tuning.