Related papers: Predicting the Evolution of Photospheric Magnetic …
The magnetic fields in the solar atmosphere structure the plasma, store free magnetic energy and produce a wide variety of active solar phenomena, like flare and coronal mass ejections(CMEs). The distribution and strength of magnetic fields…
This thesis tackles the subject of spatio-temporal forecasting with deep learning. The motivating application at Electricity de France (EDF) is short-term solar energy forecasting with fisheye images. We explore two main research directions…
Identifying solar active regions (ARs), which consist of one or more pairs of magnetic patches with opposite polarities, is essential due to their significant role in dynamic solar atmospheric phenomena. In this study, we analyze ARs during…
The observations of the Sun have been performed over the years, even centuries- Whether are there active longitudes? If yes how stable are they? One of the first The Wilcox Solar Observatory data taken over three cycles N 21, N 22, N 23…
Magnetic fields significantly influence the evolution of protoplanetary disks and the formation of planets, following the predictions of numerous magnetohydrodynamic (MHD) simulations. However, these predictions are yet observationally…
Strong solar magnetic fields are the energy source of intense flares and energetic coronal mass ejections of space weather importance. The key issue is the difficulty in predicting the occurrence time and location of strong solar eruptions,…
Although systematic measurements of the solar polar magnetic field exist only from mid 1970s, other proxies can be used to infer the polar field at earlier times. The observational data indicate a strong correlation between the polar field…
Human motion prediction is essential for the safe and smooth operation of mobile service robots and intelligent vehicles around people. Commonly used neural network-based approaches often require large amounts of complete trajectories to…
This paper describes a new 2D model for the photospheric evolution of the magnetic carpet. It is the first in a series of papers working towards constructing a realistic 3D non-potential model for the interaction of small-scale solar…
We investigate the use of Long Short-Term Memory (LSTM) and Decomposition-LSTM (DLSTM) networks, combined with an ensemble algorithm, to predict solar flare occurrences using time-series data from the GOES catalog. The dataset spans from…
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…
Although the magnetic fields in the quiet Sun account for the majority of the magnetic energy in the solar photosphere, inferring their exact spatial distribution, origin, and evolution poses an important challenge because the signals lie…
Grain Growth strongly influences the mechanical behavior of materials, making its prediction a key objective in microstructural engineering. In this study, several deep learning approaches were evaluated, including recurrent neural networks…
Large-scale velocity fields in the solar photosphere remain a mystery in spite of many years of intensive studies. In this thesis, the new method of the measurements of the solar photospheric flow fields is proposed. It is based on local…
We estimate the spatial distribution of heterogeneous physical parameters involved in the formation of magnetic domain patterns of polycrystalline thin films by using convolutional neural networks. We propose a method to obtain a spatial…
Magnetic flux generated within the solar interior emerges to the surface, forming active regions (ARs) and sunspots. Flux emergence may trigger explosive events, such as flares and coronal mass ejections and therefore understanding…
In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi-step timescales, with intermediate states either…
We establish a time-stepping learning algorithm and apply it to predict the solution of the partial differential equation of motion in micromagnetism as a dynamical system depending on the external field as parameter. The data-driven…
In order to understand the influence of magnetic fields on the propagation properties of waves, as derived from different local helioseismology techniques, forward modeling of waves is required. Such calculations need a model in…
Large scale solar magnetic field topology has a great influence on the structure of the corona, heliosphera and geomagnetic perturbations. Data obtained over the last three solar cycles have been analysed to reveal the relationships between…