J4 ›› 2015, Vol. 42 ›› Issue (5): 147-153+206.doi: 10.3969/j.issn.1001-2400.2015.05.025

• 研究论文 • 上一篇    下一篇



  1. (1. 武汉大学 电子信息学院,湖北 武汉  430072;
    2. 中国地震局 地震预测所,北京  100036;
    3. 中国电波传播研究所,山东 青岛  266107)
  • 收稿日期:2014-05-10 出版日期:2015-10-20 发布日期:2015-12-03
  • 通讯作者: 李美玲
  • 作者简介:李美玲(1989-),女,武汉大学硕士研究生,E-mail: meilingli@whu.edu.cn.
  • 基金资助:


On the short-term regional prediction of foF2 based on the support vector machine

LI Meiling1;HU Yaogai1;ZHOU Chen1;ZHAO Zhengyu1;ZHANG Yuannong1;LIU Jing2;DENG Zhongxin3   

  1. (1. School of Electronic Information, Wuhan Univ., Wuhan  430072, China;
    2. Institute of Seismology, China Earthquake Administration, Beijing  100036, China;
    3. China Research Institute of Radio Wave Propagation, Qingdao  266107, China)
  • Received:2014-05-10 Online:2015-10-20 Published:2015-12-03
  • Contact: LI Meiling



关键词: 支持向量机, 电离层foF2, 区域预报, 对比分析


Ionospheric short-term forecasting is very important to radio communication, navigation and radar systems. In this paper, in order to improve the regional prediction accuracy of ionosphere, a model of regional prediction of the ionospheric F2 layer critical frequency in China area 1 hour in advance is set up based on the support vector machine (Support Vector Machine, referred to as SVM for short) method. In this model, the influence of solar activity, geomagnetic activity, the upper atmosphere, geographical location and other factors on the ionosphere is taken into consideration. Results of this model is compared to Back-Propagation referred to as BP for short the neural network of the same input parameters and the IRI model (International Reference Ionosphere, referred to as IRI for short). The results show that the average relative error of annual prediction of SVM in high solar activity years decreases by 2.5% and 9.6%, respectively, compared with the neural network and the IRI models and in low solar activity  decreases by 1.8% and 7.5%, respectively. In the low latitude area, the prediction of SVM has more significant advantages over the BP neural network. In the high and low solar activity years it decreases by 3.2% and 2.7%, respectively. During the storm time SVM also shows a relatively good prediction ability. This proves that the developed model based on SVM in the paper has more advantages over the BP neural network and IRI model.

Key words: support vector machine, ionospheric foF2, regional prediction, comparative analysis