首页 | 本学科首页   官方微博 | 高级检索  
     检索      

变化地磁场预测的支持向量机建模
引用本文:易世华,刘代志,何元磊,齐玮.变化地磁场预测的支持向量机建模[J].地球物理学报,2013,56(1):127-135.
作者姓名:易世华  刘代志  何元磊  齐玮
作者单位:第二炮兵工程大学, 西安 710025
基金项目:国家自然科学基金(40974037)资助
摘    要:变化地磁场建模与预测是地磁导航、空间环境监测等领域的重要研究课题.由于变化地磁场属于日地系统中的一部分,受多种因素的制约影响,且其变化本身也具有较强的前后相关性.本文综合空间和地面监测数据,以变化地磁场地面观测数据、地方时、太阳射电流量和行星际磁场南向分量等为输入,采用支持向量机方法,建立了变化地磁场综合模型,并进行预测.结果表明,在地磁活动Kp指数小于4时,预测3 h平均绝对误差小于1.61 nT.

关 键 词:变化地磁场  地磁导航  空间环境监测  支持向量机  建模  预测  
收稿时间:2011-11-11

Modeling and forecasting of the variable geomagnetic field by support vector machine
YI Shi-Hua , LIU Dai-Zhi , HE Yuan-Lei , QI Wei.Modeling and forecasting of the variable geomagnetic field by support vector machine[J].Chinese Journal of Geophysics,2013,56(1):127-135.
Authors:YI Shi-Hua  LIU Dai-Zhi  HE Yuan-Lei  QI Wei
Institution:The Second Artillery Engineering University, Xi'an 710025, China
Abstract:Modeling and forecasting of the variable geomagnetic field is an important research topic in geomagnetic navigation and space environment monitoring. The variable geomagnetic field belongs to the sun-earth system, it depends on a variety of factors, and the present value of the variable geomagnetic field is related to the past. In this paper, we established the comprehensive model of variable geomagnetic field by the support vector machines. The model combines the space and ground monitoring data, and it uses the ground measuring data of the variable geomagnetic field, local time, the solar radio flux, the southern component of the interplanetary magnetic field as input. Experiments show that the mean absolute error of the model forecasting three hours are less than 1.61 nT when Kp is less than 4.
Keywords:Variable geomagnetic field  Geomagnetic navigation  Space environment  Support vector machine  Modeling  Forecasting
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《地球物理学报》浏览原始摘要信息
点击此处可从《地球物理学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号