Solar farside magnetograms from deep learning analysis of STEREO/EUVI data

Solar magnetograms are important for studying solar activity and predicting space weather disturbances1. Farside magnetograms can be constructed from local helioseismology without any farside data2-4, but their quality is lower than that of typical frontside magnetograms. Here we generate farside solar magnetograms from STEREO/Extreme UltraViolet Imager (EUVI) 304-Å images using a deep learning model based on conditional generative adversarial networks (cGANs). We train the model using pairs of Solar Dynamics Observatory (SDO)/Atmospheric Imaging Assembly (AIA) 304-Å images and SDO/Helioseismic and Magnetic Imager (HMI) magnetograms taken from 2011 to 2017 except for September and October each year. We evaluate the model by comparing pairs of SDO/HMI magnetograms and cGAN-generated magnetograms in September and October. Our method successfully generates frontside solar magnetograms from SDO/AIA 304-Å images and these are similar to those of the SDO/HMI, with Hale-patterned active regions being well replicated. Thus we can monitor the temporal evolution of magnetic fields from the farside to the frontside of the Sun using SDO/HMI and farside magnetograms generated by our model when farside extreme-ultraviolet data are available. This study presents an application of image-to-image translation based on cGANs to scientific data.Farside solar magnetograms are generated from STEREO images using deep learning, with Hale-patterned active regions being well reproduced. These images can be used to monitor the temporal evolution of magnetic fields from the farside to the frontside.

[1]  E. Christian,et al.  The STEREO Mission: An Introduction , 2008 .

[2]  H. Mason,et al.  CHIANTI—AN ATOMIC DATABASE FOR EMISSION LINES. XII. VERSION 7 OF THE DATABASE , 2012 .

[3]  C. Lindsey,et al.  Seismic Imaging of the Far Hemisphere of the Sun , 2001 .

[4]  Yang Liu,et al.  Comparison of Line-of-Sight Magnetograms Taken by the Solar Dynamics Observatory/Helioseismic and Magnetic Imager and Solar and Heliospheric Observatory/Michelson Doppler Imager , 2012 .

[5]  S. Solanki,et al.  The solar magnetic field , 2006, 1008.0771.

[6]  C. J. Wolfson,et al.  The Atmospheric Imaging Assembly (AIA) on the Solar Dynamics Observatory (SDO) , 2011 .

[7]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[8]  C. J. Wolfson,et al.  Design and Ground Calibration of the Helioseismic and Magnetic Imager (HMI) Instrument on the Solar Dynamics Observatory (SDO) , 2012 .

[9]  Solar Magnetic Field , 2006 .

[10]  H. Mason,et al.  CHIANTI - an atomic database for emission lines - I. Wavelengths greater than 50 Å , 1997 .

[11]  W. Pesnell,et al.  The Solar Dynamics Observatory (SDO) , 2012 .

[12]  M. Aschwanden,et al.  Soft X-ray Fluxes of Major Flares Far Behind the Limb as Estimated Using STEREO EUV Images , 2013, 1304.4163.

[13]  C. J. Wolfson,et al.  Sun Earth Connection Coronal and Heliospheric Investigation (SECCHI) , 2008 .

[14]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  C. Lindsey,et al.  Seismic images of the far side of the Sun , 2000, Science.

[16]  C. Lindsey,et al.  Seismic imaging of the Sun's far hemisphere and its applications in space weather forecasting , 2017, Space weather : the international journal of research & applications.