We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24 hr. Machine learning is used to devise algorithms that can learn from and make decisions on a huge amount of data. We used solar observation data during the period 2010-2015, such as vector magnetograms, ultraviolet (UV) emission, and soft X-ray emission taken by the Solar Dynamics Observatory and the Geostationary Operational Environmental Satellite. We detected active regions (ARs) from the full-disk magnetogram, from which ∼60 features were extracted with their time differentials, including magnetic neutral lines, the current helicity, the UV brightening, and the flare history. After standardizing the feature database, we fully shuffled and randomly separated it into two for training and testing. To investigate which algorithm is best for flare prediction, we compared three machine-learning algorithms: the support vector machine, k-nearest neighbors (k-NN), and extremely randomized trees. The prediction score, the true skill statistic, was higher than 0.9 with a fully shuffled data set, which is higher than that for human forecasts. It was found that k-NN has the highest performance among the three algorithms. The ranking of the feature importance showed that previous flare activity is most effective, followed by the length of magnetic neutral lines, the unsigned magnetic flux, the area of UV brightening, and the time differentials of features over 24 hr, all of which are strongly correlated with the flux emergence dynamics in an AR.
We developed a solar flare prediction model using a deep neural network (DNN), named Deep Flare Net (DeFN). The model can calculate the probability of flares occurring in the following 24 h in each active region, which is used to determine the most likely maximum classes of flares via a binary classification (e.g., ≥M class versus
We show examples of excitation of coronal waves by flare-related abrupt eruptions of magnetic rope structures. The waves presumably rapidly steepened into shocks and freely propagated afterwards like decelerating blast waves that showed up as Moreton waves and EUV waves. We propose a simple quantitative description for such shock waves to reconcile their observed propagation with drift rates of metric type II bursts and kinematics of leading edges of coronal mass ejections (CMEs). Taking account of different plasma density falloffs for propagation of a wave up and along the solar surface, we demonstrate a close correspondence between drift rates of type II bursts and speeds of EUV waves, Moreton waves, and CMEs observed in a few known events.
[1] In the framework of integrated numerical space weather prediction, we have developed a 3-D MHD simulation model of the solar surface-solar wind system. We report the construction method of the model and its first results. By implementing a grid system with angularly unstructured and increasing radial spacing, we realized a spherical grid that has no pole singularity and realized a fine grid size around the inner boundary and a wide-range grid up to a size of 1 AU simultaneously. The magnetic field at the inner boundary is specified by the observational data. In order to obtain the supersonic solar wind speed, parameterized source functions are introduced into the momentum and energy equations. These source functions decay exponentially in altitude as widely used in previous studies.The absolute values of the source functions are controlled so as to reflect the topology of the coronal magnetic field. They are increased inside the magnetic flux tube with subradial expansion and reduced inside the magnetic flux tube with overradial expansion. This adjustment aims to reproduce the variation of the solar wind speed according to the coronal magnetic structure. The simulation simultaneously reproduces the plasma-exit structure, the high-and low-temperature regions, the open and closed magnetic field regions in the corona, the fast and slow solar wind, and the sector structure in interplanetary space. It is confirmed from the comparison with observations that the MHD model successfully reproduces many features of both the fine solar coronal structure and the global solar wind structure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.