Related papers: Application and interpretation of deep learning fo…
Solar flare forecasting can be realized by means of the analysis of magnetic data through artificial intelligence techniques. The aim is to predict whether a magnetic active region (AR) will originate solar flares above a certain class…
We consider the flare prediction problem that distinguishes flare-imminent active regions that produce an M- or X-class flare in the future 24 hours, from quiet active regions that do not produce any flare within $\pm 24$ hours. Using…
Solar flares are caused by magnetic eruptions in active regions (ARs) on the surface of the sun. These events can have significant impacts on human activity, many of which can be mitigated with enough advance warning from good forecasts. To…
A solar active region can significantly disrupt the Sun Earth space environment, often leading to severe space weather events such as solar flares and coronal mass ejections. As a consequence, the automatic classification of active region…
Space weather phenomena such as solar flares, have massive destructive power when reaches certain amount of magnitude. Such high magnitude solar flare event can interfere space-earth radio communications and neutralize space-earth…
Magnetic fields emerging from the Sun's interior carry information about physical processes of magnetic field generation and transport in the convection zone. Soon after appearance on the solar surface the magnetic flux gets concentrated in…
Improving the performance of solar flare forecasting is a hot topic in 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…
The spatial extension of active regions (ARs) of the Sun can vary from one case to the next. This is a problem when studying solar flares with Convolutional Neural Networks (CNNs) as they generally use input images of a fixed size.…
A long-standing problem is to predict the future flare productivity of an active region (AR) when it is on the stage of early emergence. The aim of this study is to probe two parameters of the photospheric magnetic field, both derived…
Emerging active regions are associated with convective flows on the spatial scale and lifetimes of supergranules. To understand how these flows are involved in the formation of active regions, we aim to identify where active regions emerge…
A convolutional neural network (CNN) is used to construct a new catalog for solar flares based on high resolution (1-s cadence) Geostationary Operational Environmental Satellites (GOES) soft X-ray data. The CNN is trained to identify flare…
Investigating the properties of magnetic flux emergence is one of the most important problems of solar physics. In this study we present a newly developed deep-focus time-distance measurement scheme which is able to detect strong emerging…
There is a recurring question in solar physics about whether or not electric currents are neutralized in active regions (ARs). This question was recently revisited using three-dimensional (3D) magnetohydrodynamic (MHD) numerical simulations…
Although space weather events may not directly affect human life, they have the potential to inflict significant harm upon our communities. Harmful space weather events can trigger atmospheric changes that result in physical and economic…
With machine learning entering into the awareness of the heliophysics community, solar flare prediction has become a topic of increased interest. Although machine learning models have advanced with each successive publication, the input…
Bipolar emerging flux regions (EFRs) form active regions (ARs) that generally evolve in a pre-existing magnetic environment in the solar atmosphere. Reconfiguration of the small- and large-scale magnetic connectivities is invoked to explain…
Solar active regions (ARs) are thought to be formed by magnetic fields from the convection zone. Our flux emergence simulations revealed that a strong horizontal divergent flow (HDF) of unmagnetized plasma appears at the photosphere before…
We present two recurrent neural networks (RNNs), one based on gated recurrent units and the other based on long short-term memory, for predicting whether an active region (AR) that produces an M- or X-class flare will also produce a coronal…
Magnetic flux emergence from the solar interior to the atmosphere is believed to be a key process of formation of solar active regions and driving solar eruptions. Due to the limited capability of observation, the flux emergence process is…
In this paper, we introduce a novel methodology for leveraging shape-based characteristics of magnetograms of active region (AR) patches and provide a novel capability for predicting solar flares covering the entirety of the solar disk (AR…