支持向量机用于电离层foF2的短期区域预报

doi:10.3969/j.issn.1001-2400.2015.05.025

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

支持向量机用于电离层foF2的短期区域预报

李美玲1;胡耀垓1;周晨1;赵正予1;张援农1;刘静2;邓忠新3

(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:
国家自然科学基金资助项目(41327002，41375007)；湖北省自然科学基金青年杰出人才资助项目(2011CDA099)

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. 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

摘要/Abstract

摘要：

为了提高电离层短期区域预报效果，提出了基于支持向量机方法考虑太阳活动、地磁活动、中高层大气、地理位置等因素对电离层的影响．对中国地区电离层F2层临界频率(foF2)提前1h的区域预报模型，将支持向量机的预报模型与输入同样参数的反向传播神经网络和国际参考电离层模型从多方面进行对比分析，结果显示，支持向量机模型的年平均预报相对误差相对神经网络和国际参考电离层模型在太阳活动高年分别降低了2.5％和9.6％，在太阳活动低年分别降低了1.9％和7.5％．在低纬度地区，支持向量机模型的预报优势更加显著，在高年和低年相对反向传播神经网络分别降低了3.2％和2.7％．对暴时，支持向量机模型也表现出一定的预报能力．这表明支持向量机模型应用在中国区域电离层foF2短期预报上，相对反向传播神经网络和国际参考电离层模型更有优势．

关键词: 支持向量机, 电离层foF2, 区域预报, 对比分析

Abstract:

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

李美玲;胡耀垓;周晨;赵正予;张援农;刘静;邓忠新. 支持向量机用于电离层foF2的短期区域预报[J]. J4, 2015, 42(5): 147-153+206.

LI Meiling;HU Yaogai;ZHOU Chen;ZHAO Zhengyu;ZHANG Yuannong;LIU Jing;DENG Z X. On the short-term regional prediction of foF2 based on the support vector machine[J]. J4, 2015, 42(5): 147-153+206.

参考文献

［1］ Akam A, Alberca L. Multi Regression Method for foF2 Short-term Prediction ［R］. Poland: Space Research Center, 1999: 140-142.
［2］ McNamara L F, Angling M J, Elvidge S, et al. Assimilation Procedures for Updating Ionospheric Profiles below the F2 Peak［J］. Radio Science, 2013, 48(2), 143-157.
［3］ Liu R Y, Liu S L, Xu Z H, et al. Application of Autocorrelation Method on Ionospheric Short Term Forecasting in China ［J］. Chinese Science Bulletin, 2006, 51(3): 352-357.
［4］ Zhao X K, Ning B Q, Liu L B. A Prediction Model of Short-term Ionospheric foF2 Based on AdaBoost ［J］. Advance in Space Research, 2013, 53(3): 387-394.
［5］ Sun S J, Ban P P, Chen C. An Empirical Correction Model for Low-latitude Storm-time Ionospheric foF2 Considering E×B Drift ［J］. Advance in Space Research, 2012, 49(9): 1356-1362.
［6］刘瑞源, 权坤海, 戴开良, 等. 国际参考电离层用于中国地区时的修正计算方法［J］. 地球物理学报, 1994, 37(4): 422-432.
Liu Ruiyuan, Quan Kunhai, Dai Kailiang, et al. Application of of the International Reference Ionosphere to the Revise Calculation ［J］. Chinese Journal of Geophysics, 1994, 37(4): 422-432.
［7］ Wang R P, Zhou C. Predicting foF2 in the China Region Using the Neural Networks Improved By the Genetic Algorithm［J］. Journal of Atmospheric and Solar Terrestrial Physics, 2013, 92: 7-17.
［8］刘瑞源, 王建平, 武业文, 等. 用于中国地区电离层总电子含量短期预报方法［J］. 电波科学学报, 2011, 26(1): 18-24.
Liu Ruiyuan, Wang Jianping, Wu Yewen, et al. The Short-term Ionospheric Prediction Method for Total Electron Content in China Area［J］. Chinese Journal of Radio Science, 2011, 26(1): 18-24.
［9］ Chen C, Wu Z S, Ban P P, et al. Diurnal Specification of the Ionospheric foF2 Parameter Using a Support Vector Machine ［J］. Radio Science, 2010, 45(5): 2629-2642.
［10］邓乃扬, 田英杰. 数据挖掘中的新方法［M］. 北京: 科学出版社, 2004.
［11］ Zhou C, Wang R P, Lou W, et al. Preliminary Investigation of Real Time Mapping of foF2 in Northern China Based on Oblique Ionosonde Data ［J］. Journal Geophysics Research: Space Physics, 2013, 118(5): 2536-2544.
［12］ Cander L R. Spatial Correlation of foF2 and vTEC under Quiet and Disturbed Ionospheric Conditions: a Case Study［J］. Acta Geophysica, 2007, 55(3), 410-423.
［13］徐继生, 李雪璟, 刘裔文, 等. 磁偏角和热层风对中纬电离层TEC经度分布的影响［J］. 地球物理学报, 2013, 56(5): 1425-1434.
Xu Jisheng, Li Xuejing, Liu Yiwen, el at. Effects of Declination and Thermospheric Wind on TEC Longitude in the Mid Latitude Ionospher ［J］. Chinese Journal of Geophysics, 2013, 56(5): 1425-1434.
［14］ Oyeyemi E O, Poole A W V, Mckinnell L A. On the Global Model for foF2 Using Neural Networks［J］. Radio Science, 2005, 40(6): 5347-5356.
［15］孔庆颜, 柳文, 凡俊梅, 等. 利用人工神经网络预测电离层foF2参数［J］. 地球物理学报, 2009, 52(6): 1438-1443.
Kong Qingyan, Liu Wen, Fan Junmei, et al. On the Prediction of foF2 Using Artificial Neural Networks ［J］. Chinese Journal of Geophysics, 2009, 52(6): 1438-1443.

[1]	王俊祥,黄霖,张影,倪江群,林朗. 低复杂度的增强图像来源检测算法[J]. 西安电子科技大学学报, 2021, 48(1): 96-106.
[2]	李海,尚金雷,孙婷逸,冯青,庄子波. MC-DTSVMs的双偏振气象雷达降水粒子分类方法[J]. 西安电子科技大学学报, 2020, 47(4): 132-140.
[3]	安亚利,周水生,陈丽,王保军. 鲁棒支持向量机及其稀疏算法[J]. 西安电子科技大学学报, 2019, 46(1): 64-72.
[4]	蔡艳艳;宋晓东. 针对非平衡数据分类的新型模糊SVM模型[J]. J4, 2015, 42(5): 120-124+160.
[5]	姜建国;赵媛;孟宏伟;李博. 采用类电磁机制算法的SVM决策树多分类策略[J]. J4, 2014, 41(6): 83-88.
[6]	杨曦;李洁;韩冰;高新波. 一种分层小波模型下的极光图像分类算法[J]. J4, 2013, 40(2): 18-24.
[7]	杨曦高新波李洁韩冰. 一种分层小波模型下的极光图像分类算法[J]. J4, 2013, 40(2): 18-24.
[8]	刘晓佩;卢朝阳;李静. 结合WTLBP特征和SVM的复杂场景文本定位方法[J]. J4, 2012, 39(4): 103-108.
[9]	王世强;张登福;毕笃彦;薛德友;雍霄驹. 双谱二次特征在雷达信号识别中的应用[J]. J4, 2012, 39(2): 127-132+191.
[10]	秦传东;刘三阳;张市芳. 一种肿瘤基因的支持向量机提取方法[J]. J4, 2012, 39(1): 191-196.
[11]	厍向阳;李崇贵;姚顽强. 遥感图像几何校正的支持向量机算法研究[J]. J4, 2011, 38(5): 121-128+146.
[12]	杜亚勤；洪波；郭雷；杨宁. 一种曲面拟合图像边缘特征提取算法[J]. J4, 2011, 38(3): 164-168+188.
[13]	常甜甜;刘红卫;冯筠. 多源性数据SVM集成算法研究[J]. J4, 2010, 37(1): 136-141.
[14]	杜喆;刘三阳. 最小二乘支持向量机变型算法研究 [J]. J4, 2009, 36(2): 331-337.
[15]	梁海涛;童创明;王晓丹. 基于极化高分辨距离像的SVM目标识别方法 [J]. J4, 2007, 34(7): 148-151.

支持向量机用于电离层foF2的短期区域预报

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

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0