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 ◽  
...  

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%.

2014 ◽  
Vol 4 (2) ◽  
pp. 555-564
Author(s):  
A.M Aslam

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.


1984 ◽  
Vol 86 ◽  
pp. 155-158 ◽  
Author(s):  
Giancarlo Noci

In the past years several space missions have been proposed for the study of the Sun and of the Heliosphere. These missions were intended to clarify various different aspects of solar physics. For example, the GRIST (Grazing Incidence Solar Telescope) mission was intended as a means to improve our knowledge of the upper transition region and low corona through the detection of the solar EUV spectrum with a spatial resolution larger than in previous missions; the DISCO (Dual Spectral Irradiance and Solar Constant Orbiter) and SDO (Solar Dynamics Observatory) missions were proposed to gat observational data about the solar oscillations better than those obtained from ground based instruments; the SOHO (Solar and Heliospheric Observatory) mission was initially proposed to combine the properties of GRIST with the study of the extended corona (up to several radii of heliocentric distance) by observing the scattered Ly-alpha and OVI radiation, which was also the basis of the SCE (Solar Corona Explorer) mission proposal; the development of the interest about the variability of the Sun, both in itself and for its consequences in the history of the Earth, led to propose observations of the solar constant (included in DISCO).


2017 ◽  
Vol 13 (S335) ◽  
pp. 32-35
Author(s):  
Ranadeep Sarkar ◽  
Nandita Srivastava ◽  
Sajal Kumar Dhara

AbstractWe have studied the dynamics of the solar active region (AR) NOAA 12192 using full-disc continuum images and the vector magnetograms observed by the Helioseismic and Magnetic Imager (HMI) onboard Solar Dynamics Observatory (SDO). AR 12192 is the largest region of the solar cycle 24. It underwent a noticeable growth and produced 6 X-class, 22 M-class and 53 C-class flares during its disc passage. But the most peculiar fact of this AR is that it was associated with only one CME in spite of producing several X-class flares. In this work, we present the area evolution of this giant sunspot group during the first three rotations when it appeared as AR 12172, AR 12192 and AR 12209, respectively. We have also attempted to make a comparative study of the flare-related photospheric magnetic field and Lorentz force changes for both the eruptive and non-eruptive flares produced by AR 12192.


2010 ◽  
Vol 6 (S273) ◽  
pp. 51-55 ◽  
Author(s):  
Fraser Watson ◽  
Lyndsay Fletcher

AbstractThe automated detection of solar features is a technique which is relatively underused but if we are to keep up with the flow of data from spacecraft such as the recently launched Solar Dynamics Observatory, then such techniques will be very valuable to the solar community. Automated detection techniques allow us to examine a large set of data in a consistent way and in relatively short periods of time allowing for improved statistics to be carried out on any results obtained. This is particularly useful in the field of sunspot study as catalogues can be built with sunspots detected and tracked without any human intervention and this provides us with a detailed account of how various sunspot properties evolve over time. This article details the use of the Sunspot Tracking And Recognition Algorithm (STARA) to create a sunspot catalogue. This catalogue is then used to analyse the magnetic fields in sunspot umbrae from 1996-2010, taking in the whole of solar cycle 23.


Author(s):  
Zety Sharizat Hamidi ◽  
N.N.M. Shariff

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.


2020 ◽  
Vol 498 (1) ◽  
pp. L104-L108 ◽  
Author(s):  
H Wei ◽  
Z Huang ◽  
Z Hou ◽  
Y Qi ◽  
H Fu ◽  
...  

ABSTRACT As one of the most common features in the solar atmosphere, filaments are significant not only in solar physics but also in stellar and laboratory plasma physics. With the New Vacuum Solar Telescope and the Solar Dynamics Observatory, here we report on multi-wavelength observations of eruptions of a small (30 arcsec) filament (SF) and its consequences while interacting with ambient magnetic features including a large (300 arcsec) filament (LF). The eruptions of the SF drive a two-side-loop jet that is a result of magnetic reconnection between the SF threads and an overlying magnetic channel. As a consequence of the eruption, the heating in the footpoints of the SF destabilizes the barbs of the LF rooted nearby. Supersonic chromospheric plasma flows along the barbs of the LF are then observed in the H α passband and they apparently feed materials to the LF. We suggest that they are shock-driven plasma flows or chromospheric evaporations, which can both be the consequences of heating in the chromosphere by non-thermal particles generated in the magnetic reconnection associated with the two-side-loop jet. Our observations demonstrate that the destabilization in the vicinity of the footpoints of a barb can drive chromospheric plasma feeding to the filament.


2020 ◽  
Vol 72 (1) ◽  
Author(s):  
Shinsuke Imada ◽  
Kengo Matoba ◽  
Masashi Fujiyama ◽  
Haruhisa Iijima

AbstractWe studied temporal variation of the differential rotation and poleward meridional circulation during solar cycle 24 using the magnetic element feature tracking technique. We used line-of-sight magnetograms obtained using the helioseismic and magnetic imager aboard the Solar Dynamics Observatory from May 01, 2010 to March 26, 2020 (for almost the entire period of solar cycle 24, Carrington rotation from 2096 to 2229) and tracked the magnetic element features every 1 h. We also estimated the differential rotation and poleward meridional flow velocity profiles. The observed profiles are consistent with those of previous studies on different cycles. Typical properties resulting from torsional oscillations can also be observed from solar cycle 24. The amplitude of the variation was approximately ±10 m s$$^{-1}$$ - 1 . Interestingly, we found that the average meridional flow observed in solar cycle 24 is faster than that observed in solar cycle 23. In particular, during the declining phase of the cycle, the meridional flow of the middle latitude is accelerated from 10 to 17 m s$$^{-1}$$ - 1 , which is almost half of the meridional flow itself. The faster meridional flow in solar cycle 24 might be the result of the weakest cycle during the last 100 years.


2020 ◽  
Author(s):  
Shinsuke Imada ◽  
Kengo Matoba ◽  
Masashi Fujiyama ◽  
Haruhisa Iijima

Abstract We studied temporal variation of the differential rotation and poleward meridional circulation during solar cycle 24 using the magnetic element feature tracking technique. We used line-of-sight magnetograms obtained using the Helioseismic and Magnetic Imager aboard the Solar Dynamics Observatory from May 01, 2010 to March 26, 2020 (for almost the entire period of solar cycle 24, Carrington Rotation from 2096 to 2229) and tracked the magnetic element features every 1 hour. We also estimated the differential rotation and poleward meridional flow velocity profiles. The observed profiles are consistent with those of previous studies on different cycles. Typical properties resulting from torsional oscillations can also be observed from solar cycle 24. The amplitude of the variation was approximately $\pm$10 m s$^{-1}$. Interestingly, we found that the average meridional flow observed in solar cycle 24 is faster than that observed in solar cycle 23. In particular, during the declining phase of the cycle, the meridional flow of the middle latitude is accelerated from 10 to 17 m s$^{-1}$, which is almost half of the meridional flow itself. The faster meridional flow in solar cycle 24 might be the result of the weakest cycle during the last 100 years.


2019 ◽  
Vol 2019 ◽  
pp. 1-9 ◽  
Author(s):  
Zongxia Xie ◽  
Chunyang Ji

Automatic detection of solar events, especially uncommon events such as coronal dimming (CD) and coronal wave (CW), is very important in solar physics research. The CD and CW are not only related to the detection of coronal mass ejections (CMEs) but also affect space weather. In this paper, we have studied methods for automatically detecting them. In addition, we have collected and processed a dataset that includes the solar images and event records, where the solar images come from the Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) and the event records come from Heliophysics Event Knowledgebase (HEK). Different from the methods used before, we introduce the idea of deep learning. We train single-wavelength and multiwavelength models based on Faster R-CNN. In terms of accuracy, the single-wavelength model performs better. The multiwavelength model has a better detection performance on multiple solar events than the single-wavelength model.


Sign in / Sign up

Export Citation Format

Share Document