Reconstructing Synthetic SDO/AIA 193 A EUV Images from He I 10830 A Observations with Diffusion Model Translator

๐Ÿ“… 2026-06-07
๐Ÿ“ˆ Citations: 0
โœจ Influential: 0
๐Ÿ“„ PDF
๐Ÿค– AI Summary
This study addresses the scarcity of extreme ultraviolet (EUV) coronal observations prior to the EUV imaging era, which has hindered investigations into long-term, large-scale coronal evolution. To overcome this limitation, the authors propose a coronal holeโ€“aware diffusion model (CH-aware DMT), the first application of conditional diffusion-based image translation to synthesize physically plausible SDO/AIA 193 ร… EUV images from historical He I 10830 ร… observations. Trained on co-registered SOLIS and AIA data and incorporating coronal hole priors, the modelโ€™s generalization capability is validated using a monthly stratified evaluation strategy. Experimental results demonstrate high fidelity between reconstructed and actual EUV images (full-disk correlation coefficient CC = 0.92; coronal hole region CC = 0.84). The method successfully extends EUV-like coronal reconstructions back to 1974, showing strong agreement with SOHO/EIT, Yohkoh/SXT observations, and solar activity indices, thereby substantially expanding the temporal coverage of EUV coronal data.
๐Ÿ“ Abstract
Routine full-disk EUV imaging has been available only since the modern era, such as SOHO and SDO. To extend EUV coronal context into earlier periods, we leverage the multi-decade availability of full-disk \HeI{} observations, whose absorption is modulated by coronal irradiance and magnetic topology and is widely used as a proxy for open-field regions. We present a diffusion-based conditional image translation framework, Coronal Hole-aware Diffusion Model Translator (CH-aware DMT), to reconstruct synthetic SDO/AIA 193 ร… EUV images from \HeI{} inputs. The model is trained on temporally co-aligned SOLIS \HeI{} and AIA 193 ร… pairs spanning 2011--2015 using a month-based split, where January--October are used for training, November is used for validation, and December for testing. On the held-out test set, the reconstructions preserve dominant full-disk EUV morphology (CC=0.92) and recover CH-related low-intensity structure (CC=0.84). We further assess historical applicability by (1) comparing reconstructed AIA 193 ร… morphology with SOHO/EIT 195 ร… over 2005--2015; (2) comparing reconstructed AIA 193 ร… images generated from KPVT \HeI{} inputs against Yohkoh/SXT soft X-ray observations; and (3) evaluating long-term reconstructed disk-integrated emission statistics against observational EUV series and independent solar activity proxies (sunspot number and F10.7 radio flux over 1974--2015). These results indicate that CH-aware DMT conditioned on \HeI{} can provide a physically plausible synthetic AIA 193 ร… coronal proxy for historical studies, supporting multi-decade analyses of large-scale coronal evolution before the direct EUV imaging was available.
Problem

Research questions and friction points this paper is trying to address.

EUV image reconstruction
He I 10830 ร…
solar corona
historical solar observations
coronal proxy
Innovation

Methods, ideas, or system contributions that make the work stand out.

diffusion model
image translation
solar corona
coronal holes
EUV reconstruction
๐Ÿ”Ž Similar Papers
No similar papers found.
๐Ÿ’ผ Related Jobs
No related jobs found.
M
Marco Marena
Department of Mechanical and Industrial Engineering, New Jersey Institute of Technology
Q
Qin Li
Department of Physics, New Jersey Institute of Technology
Haimin Wang
Haimin Wang
New Jersey Institute of Technology
PhysicsSpace Science
Haodi Jiang
Haodi Jiang
Assistant Professor, Sam Houston State Univeristy
Machine LearningComputer VisionSolar PhysicsSpace WeatherCybersecurity
P
Prajwal Shah
Department of Computer Science, New Jersey Institute of Technology
Bo Shen
Bo Shen
Assistant Professor, New Jersey Institute of Technology
physics-aware generative AIHeliophysicssmart manufacturing