摘要
针对传统的欧拉(Euler)矢量法在具有复杂构造运动的区域地区内构建GPS速度场模型精度低的问题,该文提出了欧拉矢量法结合遗传算法(GA)和BP神经网络方法来构建区域GPS速度场。以云南区域1999—2015年间的GPS速度场为实验数据,分别使用欧拉矢量法、遗传神经网络(GABP)、欧拉矢量结合神经网络(Euler-BP)和欧拉矢量的遗传神经网络(Euler-GABP)法构建区域速度场模型。实验结果表明,相比其他3种方法,该文提出的Euler-GABP方法在构建区域GPS速度场模型是可行和有效的且精度高。
In view of the low accuracy of the traditional Euler vector method in constructing global positioning system(GPS)velocity field models in regions with complex tectonic motions,this paper proposed the Euler vector combined with the genetic neural network(Euler-GABP)method to construct the regional velocity field.Using Euler,GABP,Euler-BP and Euler-GABP methods built GPS velocity field model with the GPS velocity data of 1999-2015 in Yunnan.Experimental results showed that:compared with the other three methods,the Euler-GABP method proposed in this paper was feasible,effective and highly accurate in the construction of regional GPS velocity field model.
作者
胡顺强
王坦
管雅慧
杨振宇
HU Shunqiang;WANG Tan;GUAN Yahui;YANG Zhenyu(College of Resource Environment and Tourism,Capital Normal University,Beijing 100048,China;China Earthquake Networks Center,Beijing 100045,China)
出处
《测绘科学》
CSCD
北大核心
2021年第2期25-33,共9页
Science of Surveying and Mapping
基金
国家自然科学基金项目(41672192)。
关键词
欧拉矢量法
遗传算法
神经网络
速度场
Euler vector method
genetic algorithms
neural network
velocity field
