Related papers: Application and interpretation of deep learning fo…

We study the magnetic field evolution in the active region (AR) 12673 that produced the largest solar flare in the past decade on 2017 September 6. Fast flux emergence is one of the most prominent features of this AR. We calculate the…

This first paper in a series describes the design of a study testing whether pre-appearance signatures of solar magnetic active regions were detectable using various tools of local helioseismology. The ultimate goal is to understand…

The development of accurate forecasts of solar eruptive activity has become increasingly important for preventing potential impacts on space technologies and exploration. Therefore, it is crucial to detect Active Regions (ARs) before they…

Solar eruptive events such as coronal mass ejections and eruptive flares are frequently associated with the emergence of magnetic flux from the convection zone into the corona. We use three dimensional magnetohydrodynamic numerical…

In this work, we develop, for the first time, a supervised classification framework with class-dependent rewards (CDR) to predict $\geq$MM flares within 24 hr. We construct multiple datasets, covering knowledge-informed features and line-of…

Of all the activity observed on the Sun, two of the most energetic events are flares and Coronal Mass Ejections (CMEs). Usually, solar active regions that produce large flares will also produce a CME, but this is not always true (Yashiro et…

In this article, the physical processes occurring in the convective layer and the photosphere of the Sun and their connection to the formation of active regions (ARs) and the development of the corresponding magnetic field are explored.…

Solar flare forecasting mainly relies on photospheric magnetograms and associated physical features to predict forthcoming flares. However, it is believed that flare initiation mechanisms often originate in the chromosphere and the lower…

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of…

A deep learning model is often considered a black-box model, as its internal workings tend to be opaque to the user. Because of the lack of transparency, it is challenging to understand the reasoning behind the model's predictions. Here, we…

Active regions (ARs) appear in the solar atmosphere as a consequence of the emergence of magnetic flux-ropes (FR). In this study, we use Bayesian methods to analyze line-of-sight magnetograms of emerging ARs. We employ a FR model consisting…

The emergence of active regions on the Sun is an integral feature of the solar dynamo mechanism. However, details about the generation of active-region-scale magnetism and the journey of this magnetic flux to the photosphere are still in…

Understanding the influence of surface roughness on drag forces remains a significant challenge in fluid dynamics. This paper presents a convolutional neural network (CNN) that predicts drag solely by the topography of rough surfaces and is…

Several studies have correlated observations of impulsive solar activity -- flares and coronal mass ejections (CMEs) -- with the amount of magnetic flux near strong-field polarity inversion lines (PILs) in active regions' photospheric…

Solar eruptive events, like flares and coronal mass ejections, are characterized by the rapid release of energy that can give rise to emission of radiation across the entire electromagnetic spectrum and to an abrupt significant increase in…

We present a novel approach to perform ground-based estimation and prediction of the surface solar irradiance with the view to predicting photovoltaic energy production. We propose the use of mini-batch k-means clustering to extract…

It is widely accepted that solar active regions including sunspots are formed by the emerging magnetic flux from the deep convection zone. In previous numerical simulations, we found that the horizontal divergent flow (HDF) occurs before…

Active regions (ARs) play an important role in the magnetic dynamics of the Sun. Solar surface flux transport models (SFTMs) are used to describe the evolution of the radial magnetic field at the solar surface. There is however uncertainty…

Accurate and reliable predictions of solar flares are essential due to their potentially significant impact on Earth and space-based infrastructure. Although deep learning models have shown notable predictive capabilities in this domain,…

Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting…