scholarly journals Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image

2019 ◽  
Vol 2019 ◽  
pp. 1-10
Author(s):  
Dong Zhao ◽  
Long Xu ◽  
Linjie Chen ◽  
Yihua Yan ◽  
Ling-Yu Duan
Keyword(s):  
Image Reconstruction ◽  
Solar Flare ◽  
Dynamic Range ◽  
Imaging System ◽  
Solar Observation ◽  
Missing Information ◽  
Solar Dynamics Observatory ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Solar Dynamics

Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.

Observations for the Role of Flux rope Eruption in a Geoeffective Solar Flare

2014 ◽  
Vol 4 (2) ◽  
pp. 555-564
Author(s):  
A.M Aslam
Keyword(s):  
Solar Flare ◽  
Flux Rope ◽  
Magnetic Configuration ◽  
Solar Dynamics Observatory ◽  
Multi Wavelength ◽  
Solar Dynamics ◽  
Halo Coronal Mass Ejection ◽  
Mass Ejection ◽  
The Waves

On September 24, 2011 a solar flare of M 7.1 class was released from the Sun. The flare was observed by most of the space and ground based observatories in various wavebands. We have carried out a study of this flare to understand its causes on Sun and impact on earth. The flare was released from NOAA active region AR 11302 at 12:33 UT. Although the region had already produced many M class flares and one X- class flare before this flare, the magnetic configuration was not relaxed and still continued to evolve as seen from HMI observations. From the Solar Dynamics Observatory (SDO) multi-wavelength (131 Ã…, 171 Ã…, 304 Ã… and 1600Ã…) observations we identified that a rapidly rising flux rope triggered the flare although HMI observations revealed that magnetic configuration did not undergo a much pronounced change. The flare was associated with a halo Coronal Mass Ejection (CME) as recorded by LASCO/SOHO Observations. The flare associated CME was effective in causing an intense geomagnetic storm with minimum Dst index -103 nT. A radio burst of type II was also recorded by the WAVES/WIND. In the present study attempt is made to study the nature of coupling between solar transients and geospace.

Image Reconstruction Algorithm Based on Improved Super-Resolution Generative Adversarial Network

2021 ◽  
Vol 58 (8) ◽  
pp. 0810005
Author(s):  
查体博 Zha Tibo ◽  
罗林 Luo Lin ◽  
杨凯 Yang Kai ◽  
张渝 Zhang Yu ◽  
李金龙 Li Jinlong
Keyword(s):  
Image Reconstruction ◽  
Super Resolution ◽  
Reconstruction Algorithm ◽  
Generative Adversarial Network ◽  
Image Reconstruction Algorithm ◽  
Adversarial Network

scholarly journals DRGAN: a deep residual generative adversarial network for PET image reconstruction

2020 ◽  
Vol 14 (9) ◽  
pp. 1690-1700
Author(s):  
Qianqian Du ◽  
Yan Qiang ◽  
Wenkai Yang ◽  
Yanfei Wang ◽  
Yong Ma ◽  
...  
Keyword(s):  
Image Reconstruction ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Pet Image Reconstruction

scholarly journals Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3941 ◽  
Author(s):  
Li ◽  
Cai ◽  
Wang ◽  
Zhang ◽  
Tang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Imaging System ◽  
Reconstruction Method ◽  
Ct Reconstruction ◽  
Reconstruction Algorithms ◽  
Generative Adversarial Network ◽  
Image Domain ◽  
Adversarial Network ◽  
Domain Loss ◽  
Limited Angle

Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90°. We call this kind of serious limited-angle problem the ultra-limited-angle problem, which is difficult to effectively alleviate by traditional iterative reconstruction algorithms. With the development of deep learning, the generative adversarial network (GAN) performs well in image inpainting tasks and can add effective image information to restore missing parts of an image. In this study, given the characteristic of GAN to generate missing information, the sinogram-inpainting-GAN (SI-GAN) is proposed to restore missing sinogram data to suppress the singularity of the truncated sinogram for ultra-limited-angle reconstruction. We propose the U-Net generator and patch-design discriminator in SI-GAN to make the network suitable for standard medical CT images. Furthermore, we propose a joint projection domain and image domain loss function, in which the weighted image domain loss can be added by the back-projection operation. Then, by inputting a paired limited-angle/180° sinogram into the network for training, we can obtain the trained model, which has extracted the continuity feature of sinogram data. Finally, the classic CT reconstruction method is used to reconstruct the images after obtaining the estimated sinograms. The simulation studies and actual data experiments indicate that the proposed method performed well to reduce the serious artifacts caused by ultra-limited-angle scanning.

scholarly journals Enormous Eruption of 2.2 X-Class Solar Flares on 10th June 2014

2014 ◽  
Vol 36 ◽  
pp. 249-257 ◽  
Author(s):  
Zety Sharizat Hamidi ◽  
N.N.M. Shariff
Keyword(s):  
Active Region ◽  
Solar Flare ◽  
The Sun ◽  
X Rays ◽  
Solar Dynamics Observatory ◽  
Time Data ◽  
High Frequencies ◽  
The North ◽  
Solar Dynamics ◽  
Radio Blackout

The observational of active region emission of the Sun contain an critical answer of the time-dependence of the underlying heating mechanism. In this case, we investigate an X2.2 solar flare from a new Active Region AR2087 on the southeast limb of the Sun. The solar flare peaked in the X-rays is around 11:42 UT. It was found that the snapshot of this event from the Solar Dynamics Observatory (SDO) channel with the GOES X-ray plot overlayed. The flare is very bright causes by a diffraction pattern. We explore a parameter space of heating and coronal loop properties. Based on the wavelength, it shows plasma around 6 million Kelvin. At the same time, data from the NOAA issued an R3 level radio blackout, which is centered on Earth where the Sun is currently overhead at the North Africa region. This temporary blackout is caused by the heating of the upper atmosphere from the flare. The blackout level is now at an R1 and this will soon pass. Other than the temporary radio blackout for high frequencies centered over Africa this event will not have a direct impact on us. Until now, we await more data concerning a possible Coronal Mass Ejections (CMEs) but anything would more than likely not head directly towards Earth. An active region AR2087 just let out an X1.5 flare peaking at 12:52 UT. This shows plasmas with temperatures up to about 10 Million Kelvin. This event is considered one of the massive eruption of the Sun this year.

scholarly journals Fine-grained Solar Flare Forecasting Based on the Hybrid Convolutional Neural Networks*

2021 ◽  
Vol 922 (2) ◽  
pp. 232
Author(s):  
Zheng Deng ◽  
Feng Wang ◽  
Hui Deng ◽  
Lei. Tan ◽  
Linhua Deng ◽  
...  
Keyword(s):  
Solar Cycle ◽  
Solar Flare ◽  
Solar Physics ◽  
Forecast Model ◽  
Research Field ◽  
Generative Adversarial Networks ◽  
Solar Dynamics Observatory ◽  
Solar Dynamics ◽  
The Stability ◽  
Class Flare

Abstract Improving the performance of solar flare forecasting is a hot topic in the solar physics research field. Deep learning has been considered a promising approach to perform solar flare forecasting in recent years. We first used the generative adversarial networks (GAN) technique augmenting sample data to balance samples with different flare classes. We then proposed a hybrid convolutional neural network (CNN) model (M) for forecasting flare eruption in a solar cycle. Based on this model, we further investigated the effects of the rising and declining phases for flare forecasting. Two CNN models, i.e., M rp and M dp, were presented to forecast solar flare eruptions in the rising phase and declining phase of solar cycle 24, respectively. A series of testing results proved the following. (1) Sample balance is critical for the stability of the CNN model. The augmented data generated by GAN effectively improved the stability of the forecast model. (2) For C-class, M-class, and X-class flare forecasting using Solar Dynamics Observatory line-of-sight magnetograms, the means of the true skill statistics (TSS) scores of M are 0.646, 0.653, and 0.762, which improved by 20.1%, 22.3%, and 38.0% compared with previous studies. (3) It is valuable to separately model the flare forecasts in the rising and declining phases of a solar cycle. Compared with model M, the means of the TSS scores for No-flare, C-class, M-class, and X-class flare forecasting of the M rp improved by 5.9%, 9.4%, 17.9%, and 13.1%, and those of the M dp improved by 1.5%, 2.6%, 11.5%, and 12.2%.

Sign in / Sign up

Export Citation Format

Share Document