Generation of High-resolution Solar Pseudo-magnetograms from Ca ii K Images by Deep Learning

Abstract

In this Letter, we generate realistic high-resolution (1024 × 1024 pixels) pseudo-magnetograms from Ca ii K images using a deep learning model based on conditional generative adversarial networks. For this, we consider a model “pix2pixHD” that is specifically devised for high-resolution image translation tasks. We use Ca ii K 393.3 nm images from the Precision Solar Photometric Telescope at the Rome Observatory and line-of-sight magnetograms from the Helioseismic and Magnetic Imager (HMI) at the Solar Dynamics Observatory from 2011 January to 2015 June. 2465 pairs of Ca ii K and HMI are used for training except for January and July data. The remaining 436 pairs are used for an evaluation of the model. Our model shows that the mean correlation coefficient (CC) of total unsigned magnetic flux between AI-generated and real ones is 0.99 and the mean pixel-to-pixel CC after 8 × 8 binning over the full disk is 0.74. We find that the AI-generated absolute magnetic flux densities are highly consistent with real ones, even to the fine scale structures of quiet regions. On the other hand, the mean pixel-to-pixel correlations of magnetic flux densities strongly depend on a region of interest: 0.81 for active regions and 0.24 for quiet regions. Our results suggest a sufficient possibility that we can produce high-resolution solar magnetograms from historical Ca ii data.

High Resolution Solar Image Generation using Generative Adversarial Networks

“…Even though there have been some attempts for solar image generation using deep learning( [24], [25], [28], [29], [30]), most of them have focussed on the generation of Solar Farside Magnetograms or Magnetic Field observations from UV and EUV data ( [24], [29], [30]) but very few have tried to generate UV and EUV images using magnetograms( [25]). Also most of the works related to the generation of UV and EUV images from magnetograms have been using the Pix2Pix algorithm( [25]).…”

“…For this they used pairs of SDO/AIA0304-Å images and SDO/HMI magnetograms to train their deep learning model and then generated solar farside magnetograms using the STEREO/Extreme UltraViolet Imager (EUVI) 304-Å images. Shin et al [29] used the Pix2PixHD model to generate high resolution magnetograms from Ca II K images. They used pairs of Ca II K 393.3 nm images from the Precision Solar Photometric Telescope at the Rome Observatory [32] and SDO/HMI line-of-sight magnetograms to train their model.…”

Proxy-based Prediction of Solar Extreme Ultraviolet Emission Using Deep Learning

“…Here, we apply DL to map ground-based images of the 1083 nm He I line strength to contemporaneous solar images of EUV emission obtained with the Solar Dynamics Observatory (SDO) space telescope on its geosynchronous orbit (Pesnell et al 2012). The high-cadence, high spatial resolution, multiwavelength aspects of SDO lends itself to DL (Galvez et al 2019), and DL has been used to translate images of solar Ca II emission into magnetic field maps (magnetograms; Shin et al 2020), and magnetograms into solar UV/EUV (Park et al 2019). DL has also been used on solar EUV images to predict coronal holes (Illarionov et al 2020) and solar wind intensity (Upendran et al 2020).…”

Proxy-Based Prediction of Solar Extreme Ultraviolet Emission using Deep Learning

“…Here, we apply DL to map ground-based images of the 1083 nm He I line strength to contemporaneous solar images of EUV emission obtained with the Solar Dynamics Observatory (SDO) space telescope on its geosynchronous orbit (Pesnell et al 2012). The high-cadence, high spatial resolution, multi-wavelength aspects of SDO lends itself to DL (Galvez et al 2019), and DL has been used to translate images of solar Ca II emission into magnetic field maps (magnetograms) ( Shin et al 2020), and magnetograms into solar UV/EUV (Park et al 2019). DL has also been used on solar EUV images to predict coronal holes (Illarionov et al 2020) and solar wind intensity (Upendran et al 2020).…”