Data for: Forecasting Solar Flares using magnetogram-based predictors and Machine Learning

Replication Files for the paper "Forecasting Solar Flares using magnetogram-based predictors and Machine Learning". The source code is in R and the data files are simple text files. Abstract of the associated paper: We propose a forecasting approach for solar flares based on data from Solar Cycle 24, taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) mission. In particular, we use the Space-weather HMI Active Region Patches (SHARP) product that facilitates cut-out magnetograms of solar active regions (AR) in the Sun in near-realtime (NRT), taken over a five-year interval (2012 - 2016). Our approach utilizes a set of thirteen predictors, which are not included in the SHARP data, extracted from line-of-sight and vector photospheric magnetograms. We exploit several Machine Learning (ML) and Conventional Statistics techniques to predict flares of class >M1 and >C1, with a 24h forecast window. The ML methods used are Multi-Layer Perceptrons (MLP), Support Vector Machines (SVM) and Random Forests (RF). We conclude that Random Forests could be the prediction technique of choice for our sample, with the second best method being Multi-Layer Perceptrons, subject to an entropy objective function. A Monte Carlo simulation showed that the best performing method gives accuracy ACC=0.93(0.00), true skill statistic TSS=0.74(0.02) and Heidke skill score HSS=0.49(0.01) for a >M1 class flares prediction with probability threshold 15% and ACC=0.84(0.00), TSS=0.60(0.01) and HSS=0.59(0.01) for a >C1 class flares prediction with probability threshold 35%.本数据集为论文《基于磁图预测因子与机器学习的太阳耀斑预报》的复现文件。源代码采用R语言编写，数据文件为纯文本格式。 相关论文摘要如下： 我们提出了一种基于第24太阳周期观测数据的太阳耀斑预报方法，该数据由太阳动力学天文台（Solar Dynamics Observatory, SDO）搭载的日震与磁像仪（Helioseismic and Magnetic Imager, HMI）采集获得。具体而言，我们使用了空间天气HMI活动区斑块（Space-weather HMI Active Region Patches, SHARP）产品，该产品可获取太阳近实时（near-realtime, NRT）下的太阳活动区（solar active regions, AR）裁剪磁图，采集时段为2012年至2016年的五年区间。我们的方法采用了13种未包含于SHARP数据集中的额外预测因子，这些因子从视向及矢量光球磁图中提取得到。 我们采用多种机器学习（Machine Learning, ML）与传统统计技术，针对>M1级和>C1级太阳耀斑开展24小时时效的预报任务。所使用的机器学习方法包括多层感知机（Multi-Layer Perceptrons, MLP）、支持向量机（Support Vector Machines, SVM）以及随机森林（Random Forests, RF）。 实验结果表明，随机森林是本研究样本集下的最优预报方法，次优方案为基于熵目标函数的多层感知机。蒙特卡洛模拟结果显示，在概率阈值为15%的>M1级耀斑预报任务中，最优方法的准确率（ACC）为0.93(±0.00)、真实技能统计量（TSS）为0.74(±0.02)、海德克技能评分（HSS）为0.49(±0.01)；而在概率阈值为35%的>C1级耀斑预报任务中，对应指标分别为ACC=0.84(±0.00)、TSS=0.60(±0.01)以及HSS=0.59(±0.01)。