A deep learning virtual instrument for monitoring extreme UV solar spectral irradiance

Alexandre Szenicer, David F. Fouhey, Andres Munoz-Jaramillo, Paul J. Wright, Rajat Thomas, Richard Galvez, Meng Jin, Mark C.M. Cheung

Research output: Contribution to journalArticlepeer-review


Measurements of the extreme ultraviolet (EUV) solar spectral irradiance (SSI) are essential for understanding drivers of space weather effects, such as radio blackouts, and aerodynamic drag on satellites during periods of enhanced solar activity. In this paper, we show how to learn a mapping from EUV narrowband images to spectral irradiance measurements using data from NASA’s Solar Dynamics Observatory obtained between 2010 to 2014. We describe a protocol and baselines for measuring the performance of models. Our best performing machine learning (ML) model based on convolutional neural networks (CNNs) outperforms other ML models, and a differential emission measure (DEM) based approach, yielding average relative errors of under 4.6% (maximum error over emission lines) and more typically 1.6% (median). We also provide evidence that the proposed method is solving this mapping in a way that makes physical sense and by paying attention to magnetic structures known to drive EUV SSI variability.

Original languageEnglish (US)
Article numbereaaw6548
JournalScience Advances
Issue number10
StatePublished - Oct 2 2019

ASJC Scopus subject areas

  • General


Dive into the research topics of 'A deep learning virtual instrument for monitoring extreme UV solar spectral irradiance'. Together they form a unique fingerprint.

Cite this