基于神经网络并考虑地形改正的GPS水准高程拟合  

GPS Height Collocation Based on Artificial Neural Network and Effect of Terrain

作　　者：王殊伟[1] 陈正阳[1] 

机构地区：[1]中南大学信息物理工程学院,湖南长沙410083

出　　处：《海洋测绘》2006年第4期30-32,共3页Hydrographic Surveying and Charting

摘　　要：从考虑地形改正的基础出发,运用神经网络进行GPS水准高程拟合。从节约计算时间的角度提出了新的思路,认为不必深究于过密的DEM模型数据,DEM模型数据只是中间过程,能达到精度要求即可,如果过于强调其精度,相反还会带入DEM高程模型算法本身的系统误差。并提出了DEM模型的密度是否符合拟合要求的初步判定方法。还对神经网络的基本理论作了简单的概括和说明。Based on terrain, the theory of artificial neural network is used in this paper for GPS height collocation. A new theory is given to save the calculation time. This paper points out that excessive dense of DEM model is not necessary as a transition. If DEM model is paid more attention and much dense of DEM model is achieved, the system errors can be bigger and bigger from DEM calculation. Finally, a simple judgment is put forward to judge whether the density of DEM model is enough or not.

关 键 词：GPS水准高程拟合 神经网络 地形改正 数字高程模型 

分 类 号：P224[天文地球—大地测量学与测量工程]