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

人工神经网络在地震中期预报中的应用
引用本文:王炜,宋先月,王.人工神经网络在地震中期预报中的应用[J].地震,2000,20(1):10-16.
作者姓名:王炜  宋先月  
作者单位:1. 上海市地震局,上海,200062
2. 江苏省地震局,江苏,南京,210014
基金项目:中国地震局“九五”科研攻关项目!95-04
摘    要:将BP神经网络用于地震中期预报。使用一些常用的地震学指标作为神经网络的输入,而将BP神经网络的输出作为表征地震活动增强的特征参数W1,并将其用于华北地区进行空间扫描。结果表明,中强地震前1~3年未来震中周围通常出现明显的W1值中期异常区,该方法具有较好的中期预报效果。

关 键 词:BP神经网络  非线性关系  地震预报  中期预报
文章编号:1000-3274(2000)01-0010-07
修稿时间:1999-03-26

The application of artificial neural networks to mid-term earthquake prediction
WANG Wei,SONG Xian-yue,WANG Zheng-zheng.The application of artificial neural networks to mid-term earthquake prediction[J].Earthquake,2000,20(1):10-16.
Authors:WANG Wei  SONG Xian-yue  WANG Zheng-zheng
Institution:WANG Wei (Seismological Bureau of Shanghai Municipality, Shanghai 200062, China) SONG Xian-yue (Seismological Bureau of Shanghai Municipality, Shanghai 200062, China) WANG Zheng-zheng (Seismological Bureau of Jiangsu Province, Nanjing 210014, China)
Abstract:BP neural network is used in mid-term earthquake prediction. Some usual pre- diction parameters of seismology are used as input units of neural networks. And the output units of neural networks are called as the characteristic parameter W, describing enhancement of seismicity.It is used for spatial scanning in North China. The result shows that the mid-term anomaly zone of W1-value usually appears obviously around the epicen- ter about 1-3 years before future earthquakes with good prediction effect.
Keywords:BP neural network  Nonlinear relationship  Enhancement of seismicity  Mid-term earthquake prediction
本文献已被 CNKI 维普 万方数据 等数据库收录!
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