中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
利用BP神经网络预测4E指数

文献类型:期刊论文

作者李志涛 ; 薛炳森
刊名空间科学学报
出版日期2007
卷号27期号:5页码:374-378
ISSN号0254-6l24
关键词太阳风 行星际磁场 AE指数 BP神经网络
其他题名Forecasting Auroral Electrojet Activity W ithB P Neural Networks
通讯作者北京8701信箱
中文摘要采用的预报模式是一种全连接的BP网络模型,利用太阳风及行星际磁场的观测数据预报AE指数.神经网络输入选用ACE卫星数据,取5min平均值,通过比较,选用4个预报参量.构造了预报参量时续为20min,40min和60min依次递增的三个网络,分别进行训练和预测,并对行星际参量对AE指数影响的时续性进行了探讨.预报结果表明,全连接BP神经网络在AE指数的短期预报中是比较有效的,同时还提出了需要进一步改进的环节.
英文摘要Magnet0sphere substorm is the result of couplings between solar wind and m agneto-sphere.In general,as AE,AL etc indices are used to inspect the turbulence in polar region when sub storms occur,they are the target indices in space environment prediction.The AE index is predicted by data of solar wind and interplanetary magnetic field(IMF),with a back-propagation neural network,which is all-joint one.The data of input comes from ACE satellite,combined into 5 min resolution.There are 4 input variables:The B,B components of interplanetary m agnetic field,the velocity of solar wind and the density of solar wind proton.The 3 networks with the length of input time series of 20,40 and 60 minutes are constructed,trained and train them separately.Then the time series of variables on influencing the AE index is discussed.The predictions show that our network model can forecast the trend of fluctuation of AE index,having wonderful veracity in quantitatively computing index value.The correlation between four input variables(By,Bz,u,n) and AE index is very good,As the time extends,the forecasting precision needs SOlYie improvem ents.
学科主题空间环境
语种中文
源URL[http://ir.cssar.ac.cn/handle/122/232]  
专题国家空间科学中心_空间环境部
推荐引用方式
GB/T 7714
李志涛,薛炳森. 利用BP神经网络预测4E指数[J]. 空间科学学报,2007,27(5):374-378.
APA 李志涛,&薛炳森.(2007).利用BP神经网络预测4E指数.空间科学学报,27(5),374-378.
MLA 李志涛,et al."利用BP神经网络预测4E指数".空间科学学报 27.5(2007):374-378.

入库方式: OAI收割

来源:国家空间科学中心

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。