Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 4 min ago
PreprintCC BY 4.0arXiv

Cross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 Å to EUV Translation and Coronal Hole Segmentation

Abstract

The long observational record of He I 10830 Å offers a means to investigate solar morphology before modern extreme-ultraviolet (EUV) imaging. We adapt the Surya solar foundation model to predict Solar Dynamics Observatory/Atmospheric Imaging Assembly (SDO/AIA) 94, 193, and 304 Å images and a coronal hole (CH) probability map from full-disk helium observations. A convolutional input adapter, low-rank backbone updates, and dedicated output decoders learn from temporally paired, geometrically registered observations, with Spatial Possibilistic Clustering Algorithm (SPOCA) catalog polygons providing CH supervision. On observations held out from downstream fine-tuning, the selected dedicated models achieve disk-restricted correlation coefficients (CCs) of 0.8196, 0.8885, and 0.8398 for the three AIA channels, respectively; the CH model achieves an intersection over union (IoU) of 0.4360. The predictions recover broad solar structure, although local agreement varies substantially by channel. An optional residual refiner addresses spatial detail, and its application on pre-SDO dates improves the correlation of synthetic AIA 304 with Solar and Heliospheric Observatory/Extreme-ultraviolet Imaging Telescope (SOHO/EIT) 304 references from 0.6511 to 0.7085. Together, these results support the feasibility of helium-conditioned EUV morphological proxies and motivate their use in historical reconstruction, within the scope of the downstream test and cross-instrument evaluation.

Related

  1. Multi-wavelength synthesis of a flux rope-trapped mini-prominence eruption and post-flare coronal rain
    Samrat Sen, Alexander G. M. Pietrow, Veronika Jercic +1
    arXivPreprintCC BY 4.0Full textSolar & stellar physicsPlasma physicsarXiv
  2. Formation and enhancement of coronal rain induced by a large-scale coronal wave
    Xiaofan Zhang, Leping Li, Chun Xia +4
    Astronomy & AstrophysicsPeer-reviewedPublisher termsSolar & stellar physicsCrossref
  3. Unified Scaling Relation for Coronal Temperature Anomaly and Solar Wind Acceleration
    Shuai Sheng
    EGUspherePreprintCC BY 4.0Full text1 citedSolar & stellar physicsEGUsphere
  4. ACME: A synoptic representation and visual catalog of coronal mass ejection activity
    M. Flores-Soriano
    Astronomy & AstrophysicsPeer-reviewedPublisher termsSolar & stellar physicsCrossref
  5. Analysis of a coronal hole jet in the chromosphere and the transition region with IRIS and SDO observations
    M. Koletti, C. Gontikakis, S. Patsourakos +1
    Astronomy & AstrophysicsPeer-reviewedPublisher termsSolar & stellar physicsCrossref
BibTeX
@misc{marena2026crossmodal,
  title = {{Cross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 Å to EUV Translation and Coronal Hole Segmentation}},
  author = {Marco Marena and Andrés Muñoz Jaramillo and Qin Li and Haodi Jiang and Jinghao Cao and Wen He and Ziyang Zhang and Chenxi Yuan and Chao Wang and Haimin Wang and Bo Shen},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.04553},
  eprint = {2610.04553},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.04553},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Cross-Modal Solar Image Synthesis: Adapting the Surya Foundation Model from He I 10830 Å to EUV Translation and Coronal Hole Segmentation
AU  - Marco Marena
AU  - Andrés Muñoz Jaramillo
AU  - Qin Li
AU  - Haodi Jiang
AU  - Jinghao Cao
AU  - Wen He
AU  - Ziyang Zhang
AU  - Chenxi Yuan
AU  - Chao Wang
AU  - Haimin Wang
AU  - Bo Shen
PY  - 2026
DA  - 2026/10/03
PB  - arXiv
DO  - 10.48550/arxiv.2610.04553
UR  - https://arxiv.org/abs/2610.04553
AB  - The long observational record of He I 10830 Å offers a means to investigate solar morphology before modern extreme-ultraviolet (EUV) imaging. We adapt the Surya solar foundation model to predict Solar Dynamics Observatory/Atmospheric Imaging Assembly (SDO/AIA) 94, 193, and 304 Å images and a coronal hole (CH) probability map from full-disk helium observations. A convolutional input adapter, low-rank backbone updates, and dedicated output decoders learn from temporally paired, geometrically registered observations, with Spatial Possibilistic Clustering Algorithm (SPOCA) catalog polygons providing CH supervision. On observations held out from downstream fine-tuning, the selected dedicated models achieve disk-restricted correlation coefficients (CCs) of 0.8196, 0.8885, and 0.8398 for the three AIA channels, respectively; the CH model achieves an intersection over union (IoU) of 0.4360. The predictions recover broad solar structure, although local agreement varies substantially by channel. An optional residual refiner addresses spatial detail, and its application on pre-SDO dates improves the correlation of synthetic AIA 304 with Solar and Heliospheric Observatory/Extreme-ultraviolet Imaging Telescope (SOHO/EIT) 304 references from 0.6511 to 0.7085. Together, these results support the feasibility of helium-conditioned EUV morphological proxies and motivate their use in historical reconstruction, within the scope of the downstream test and cross-instrument evaluation.
ER  -