Spatiotemporal filtering using principal component analysis and Karhunen-Loeve expansion approaches for regional GPS network analysis
Spatiotemporal filtering using principal component analysis and Karhunen-Loeve expansion approaches for regional GPS network analysis
复制标题
DOI：
10.1029/2005jb003806
复制
发表时间：
2006-03-09
影响因子：
3.9
通讯作者：
Jamason, P
中科院分区：
文献类型：
--
作者：
Dong, D;Fang, P;Jamason, P
[1]空间滤波是通过减小所谓的共模误差来提高区域GPS网坐标时间序列精度的有效方法，从而为检测微弱或瞬时变形信号提供更好的分辨率。常用的区域滤波方法假定共模误差在空间上是均匀的，这对于数百公里范围的网络来说是一个很好的近似，但随着空间范围的增加而被打破。更严格的方法应该去掉空间均匀分布的假设，让数据本身揭示共模误差的空间分布。主成分分析(PCA)和卡尔胡宁-洛夫展开(KLE)都将网络时间序列分解为一组时变模式及其空间响应。因此，它们提供了执行时空过滤的数学框架。我们将主成分分析和KLE相结合应用于南加州综合GPS网(SCIGN)2000-2004年的逐日站点坐标时间序列。我们证明了空间和时间相关的共模误差是日常GPS解算中的主要误差源。与南加州GPS网络的空间范围相比，东、北、垂直分量的共模误差的空间特征接近一致，这意味着共模误差的波长源很长。此外，共模误差表现出时间上的非随机图案。
[1] Spatial filtering is an effective way to improve the precision of coordinate time series for regional GPS networks by reducing so-called common mode errors, thereby providing better resolution for detecting weak or transient deformation signals. The commonly used approach to regional filtering assumes that the common mode error is spatially uniform, which is a good approximation for networks of hundreds of kilometers extent, but breaks down as the spatial extent increases. A more rigorous approach should remove the assumption of spatially uniform distribution and let the data themselves reveal the spatial distribution of the common mode error. The principal component analysis (PCA) and the Karhunen-Loeve expansion (KLE) both decompose network time series into a set of temporally varying modes and their spatial responses. Therefore they provide a mathematical framework to perform spatiotemporal filtering. We apply the combination of PCA and KLE to daily station coordinate time series of the Southern California Integrated GPS Network (SCIGN) for the period 2000 to 2004. We demonstrate that spatially and temporally correlated common mode errors are the dominant error source in daily GPS solutions. The spatial characteristics of the common mode errors are close to uniform for all east, north, and vertical components, which implies a very long wavelength source for the common mode errors, compared to the spatial extent of the GPS network in southern California. Furthermore, the common mode errors exhibit temporally nonrandom patterns.