Generation of He i 1083 nm Images from SDO AIA Images by Deep Learning

Son, Jihyeon; Cha, Junghun; Moon, Yong‐Jae; Lee, Harim; Park, Eunsu; Shin, Gyungin; Jeong, Hyun-Jin

doi:10.3847/1538-4357/ac16dd

Cited by 10 publications

(9 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The competition between the generator and the discriminator contributes to generate realistic data. The performance of the adversarial objectives have been well demonstrated in image-to-image translation tasks for solar data (Park et al 2019;Shin et al 2020;Lim et al 2021;Son et al 2021). The Pix2PixHD model of Jeong20 uses both FM and LSGAN losses.…”

Section: Deep Learning Modelmentioning

confidence: 98%

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Jeong¹,

Moon²,

Park³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Here we greatly improve Artificial Intelligence (AI)-generated solar farside magnetograms using data sets of Solar Terrestrial Relations Observatory (STEREO) and Solar Dynamics Observatory (SDO). We modify our previous deep learning model and configuration of input data sets to generate more realistic magnetograms than before. First, our model, which is called Pix2PixCC, uses updated objective functions which include correlation coefficients (CCs) between the real and generated data. Second, we construct input data sets of our model: solar farside STEREO extreme ultraviolet (EUV) observations together with nearest frontside SDO data pairs of EUV observations and magnetograms. We expect that the frontside data pairs provide the historic information of magnetic field polarity distributions. We demonstrate that magnetic field distributions generated by our model are more consistent with the real ones than before in view of several metrics. The averaged pixel-to-pixel CC for full disk, active regions, and quiet regions between real and AI-generated magnetograms with 8 by 8 binning are 0.88, 0.91, and 0.70, respectively. Total unsigned magnetic flux and net magnetic flux of the AI-generated magnetograms are consistent with those of real ones for test data sets. It is interesting to note that our farside magnetograms produce consistent polar field strengths and magnetic field polarities with those of nearby frontside ones for solar cycle 24 and 25. Now we can monitor the temporal evolution of active regions using solar farside magnetograms by the model together with the frontside ones. Our AI-generated Solar Farside Magnetograms (AISFMs) are now publicly available at Korean Data Center (KDC) for SDO.

show abstract

Section: Deep Learning Modelmentioning

confidence: 98%

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Jeong¹,

Moon²,

Park³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The competition between the generator and the discriminator contributes to the generation of realistic data. The performance of the adversarial objectives has been well demonstrated in image-to-image translation tasks for solar data (Park et al 2019;Shin et al 2020;Lim et al 2021;Son et al 2021).…”

Section: Deep-learning Modelmentioning

confidence: 98%

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Jeong

Moon

Park

et al. 2022

ApJS

Self Cite

View full text Add to dashboard Cite

Here we greatly improve artificial intelligence (AI)–generated solar farside magnetograms using data sets from the Solar Terrestrial Relations Observatory (STEREO) and Solar Dynamics Observatory (SDO). We modify our previous deep-learning model and configuration of input data sets to generate more realistic magnetograms than before. First, our model, which is called Pix2PixCC, uses updated objective functions, which include correlation coefficients (CCs) between the real and generated data. Second, we construct input data sets of our model: solar farside STEREO extreme-ultraviolet (EUV) observations together with nearest frontside SDO data pairs of EUV observations and magnetograms. We expect that the frontside data pairs provide historic information on magnetic field polarity distributions. We demonstrate that magnetic field distributions generated by our model are more consistent with the real ones than previously, in consideration of several metrics. The averaged pixel-to-pixel CC for full disk, active regions, and quiet regions between real and AI-generated magnetograms with 8 × 8 binning are 0.88, 0.91, and 0.70, respectively. Total unsigned magnetic flux and net magnetic flux of the AI-generated magnetograms are consistent with those of real ones for the test data sets. It is interesting to note that our farside magnetograms produce polar field strengths and magnetic field polarities consistent with those of nearby frontside magnetograms for solar cycles 24 and 25. Now we can monitor the temporal evolution of active regions using solar farside magnetograms by the model together with the frontside ones. Our AI-generated solar farside magnetograms are now publicly available at the Korean Data Center for SDO (http://sdo.kasi.re.kr).

show abstract

“…They applied the generated farside magnetograms to the extrapolation of global coronal fields using a potential field source surface model. Son et al (2021) also applied the Pix2pixHD to image translation from SDO/AIA 19.3 and 30.4 nm data to National Solar Observatory/ Synoptic Optical Long-term Investigations of the Sun He I 1083 nm data. They showed it was possible for deep learning to compensate for the limitations of ground observation, such as observation time or weather conditions.…”

Section: Introductionmentioning

confidence: 99%

Pixel-to-pixel Translation of Solar Extreme-ultraviolet Images for DEMs by Fully Connected Networks

Park

Lee

Moon

et al. 2023

ApJS

Self Cite

View full text Add to dashboard Cite

In this study, we suggest a pixel-to-pixel image translation method among similar types of filtergrams such as solar extreme-ultraviolet (EUV) images. For this, we consider a deep-learning model based on a fully connected network in which all pixels of solar EUV images are independent of one another. We use six-EUV-channel data from the Atmospheric Imaging Assembly (AIA) on board the Solar Dynamics Observatory (SDO), of which three channels (17.1, 19.3, and 21.1 nm) are used as the input data and the remaining three channels (9.4, 13.1, and 33.5 nm) as the target data. We apply our model to representative solar structures (coronal loops inside of the solar disk and above the limb, coronal bright point, and coronal hole) in SDO/AIA data and then determine differential emission measures (DEMs). Our results from this study are as follows. First, our model generates three EUV channels (9.4, 13.1, and 33.5 nm) with average correlation coefficient values of 0.78, 0.89, and 0.85, respectively. Second, our model generates the solar EUV data with no boundary effects and clearer identification of small structures when compared to a convolutional neural network–based deep-learning model. Third, the estimated DEMs from AI-generated data by our model are consistent with those using only SDO/AIA channel data. Fourth, for a region in the coronal hole, the estimated DEMs from AI-generated data by our model are more consistent with those from the 50 frames stacked SDO/AIA data than those from the single-frame SDO/AIA data.

show abstract

Generation of He i 1083 nm Images from SDO AIA Images by Deep Learning

Cited by 10 publications

References 32 publications

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Improved AI-generated Solar Farside Magnetograms by STEREO and SDO Data Sets and Their Release

Pixel-to-pixel Translation of Solar Extreme-ultraviolet Images for DEMs by Fully Connected Networks

Contact Info

Product

Resources

About