行星际日冕物质抛射(Interplanetary Coronal Mass Ejection, ICME)与地球磁层相互作用并带来地磁暴等地磁扰动.从Richardson和Cane提供的近地球ICME列表中筛选出ICME事件集,基于ICME扰动期间的行星际等离子体与磁场数据提取出特征.通...行星际日冕物质抛射(Interplanetary Coronal Mass Ejection, ICME)与地球磁层相互作用并带来地磁暴等地磁扰动.从Richardson和Cane提供的近地球ICME列表中筛选出ICME事件集,基于ICME扰动期间的行星际等离子体与磁场数据提取出特征.通过计算各特征的费舍尔分值(Fisher Score),对这些特征进行选择,发现行星际磁场南北向分量持续时间小于-10nT且激波等扰动所带来的ICME扰动开始时,太阳风速度的增量等特征与ICME事件的地磁效应密切相关.这与现有的传统统计研究结果一致.以这些特征为基础,训练得到的径向基函数支持向量机能够以0.78±0.08的准确率判断ICME事件是否会产生中等及以上强度的地磁暴(Dst≤-50nT).展开更多
The solar 10.7 cm radio flux,F_(10.7),a measure of the solar radio flux per unit frequency at a wavelength of 10.7 cm,is a key and serviceable index for monitoring solar activities.The accurate prediction of F_(10.7) ...The solar 10.7 cm radio flux,F_(10.7),a measure of the solar radio flux per unit frequency at a wavelength of 10.7 cm,is a key and serviceable index for monitoring solar activities.The accurate prediction of F_(10.7) is of significant importance for short-term or long-term space weather forecasting.In this study,we apply Back Propagation(BP)neural network technique to forecast the daily F_(10.7)based on the trial data set of F_(10.7) from 1980 to 2001.Results show that this technique is better than the other prediction techniques for short-term forecasting,such as Support Vector Regression method.展开更多
基金Supported by the National Natural Science Foundation of China(41231066)the Foundation for Ministry of Science and Technology of China(2011CB811404)+1 种基金the Specialized Research Fund for State Key Laboratories of the CASthe Scientific Research Staring Foundation for Nanjing University of Information Science and Technology(2013x030)
文摘The solar 10.7 cm radio flux,F_(10.7),a measure of the solar radio flux per unit frequency at a wavelength of 10.7 cm,is a key and serviceable index for monitoring solar activities.The accurate prediction of F_(10.7) is of significant importance for short-term or long-term space weather forecasting.In this study,we apply Back Propagation(BP)neural network technique to forecast the daily F_(10.7)based on the trial data set of F_(10.7) from 1980 to 2001.Results show that this technique is better than the other prediction techniques for short-term forecasting,such as Support Vector Regression method.
