分类: 天文学 >> 天文学 提交时间: 2023-02-19
摘要: In this paper, we consider incorporating data associated with the sun's north and south polar field strengths to improve solar flare prediction performance using machine learning models. When used to supplement local data from active regions on the photospheric magnetic field of the sun, the polar field data provides global information to the predictor. While such global features have been previously proposed for predicting the next solar cycle's intensity, in this paper we propose using them to help classify individual solar flares. We conduct experiments using HMI data employing four different machine learning algorithms that can exploit polar field information. Additionally, we propose a novel probabilistic mixture of experts model that can simply and effectively incorporate polar field data and provide on-par prediction performance with state-of-the-art solar flare prediction algorithms such as the Recurrent Neural Network (RNN). Our experimental results indicate the usefulness of the polar field data for solar flare prediction, which can improve Heidke Skill Score (HSS2) by as much as 10.1%.
分类: 天文学 >> 天文学 提交时间: 2023-02-19
摘要: 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 line-of-sight magnetograms and parameters of active regions in two data products covering Solar Cycle 23 and 24, we train and evaluate two deep learning algorithms -- CNN and LSTM -- and their stacking ensembles. The decisions of CNN are explained using visual attribution methods. We have the following three main findings. (1) LSTM trained on data from two solar cycles achieves significantly higher True Skill Scores (TSS) than that trained on data from a single solar cycle with a confidence level of at least 0.95. (2) On data from Solar Cycle 23, a stacking ensemble that combines predictions from LSTM and CNN using the TSS criterion achieves significantly higher TSS than the "select-best" strategy with a confidence level of at least 0.95. (3) A visual attribution method called Integrated Gradients is able to attribute the CNN's predictions of flares to the emerging magnetic flux in the active region. It also reveals a limitation of CNN as a flare prediction method using line-of-sight magnetograms: it treats the polarity artifact of line-of-sight magnetograms as positive evidence of flares.
分类: 天文学 >> 天文学 提交时间: 2023-02-19
摘要: We describe our first attempt to systematically simulate the solar wind during different phases of the last solar cycle with the Alfv\'en Wave Solar atmosphere Model (AWSoM) developed at the University of Michigan. Key to this study is the determination of the optimal values of one of the most important input parameter of the model, the Poynting flux, which prescribes the energy flux passing through the chromospheric boundary of the model in form of Alfv\'en wave turbulence. It is found that the optimal value of the Poynting flux parameter is correlated with: 1) the open magnetic flux with the linear correlation coefficient of 0.913; 2) the area of the open magnetic field regions with the linear correlation coefficient of 0.946. These highly linear correlations could shed light on understanding how Alfv\'en wave turbulence accelerates the solar wind during different phases of the solar cycle and estimating the Poynting flux parameter for real-time solar wind predictions with AWSoM.
分类: 天文学 >> 天文学 提交时间: 2023-02-19
摘要: Simulation of plasmas in electromagnetic fields requires numerical solution of a kinetic equation that describes the time evolution of the particle distribution function. In this paper we propose a finite volume scheme based on integral relation for Poisson brackets to solve the Liouville equation, the most fundamental kinetic equation. The proposed scheme conserves the number of particles, maintains the total-variation-diminishing (TVD) property, and provides high-quality numerical results. Other types of kinetic equations may be also formulated in terms of Poisson brackets and solved with the proposed method including the transport equations describing the acceleration and propagation of Solar Energetic Particles (SEPs), which is of practical importance, since the high energy SEPs produce radiation hazards. The proposed scheme is demonstrated to be accurate and efficient, which makes it applicable to global simulation systems analyzing space weather.