向量距离中角度信息对时空Kriging的影响  

Vector distance direction information for spatio-temporal Kriging

作　　者：陈鼎新[1,2] 陆文凯[1] 刘代志 

机构地区：[1]清华大学自动化系,智能技术与系统国家重点实验室,北京100084 [2]火箭军工程大学907教研室,西安710025

出　　处：《清华大学学报（自然科学版）》2016年第5期553-557,共5页Journal of Tsinghua University(Science and Technology)

基　　金：国家自然科学基金资助项目(41374154)

摘　　要：时空Kriging算法的核心,是将变差函数的概念扩展到时空域,变差函数的构建过程基础是计算时间切片和空间切片的向量距离。该文讨论了向量距离对构建时空变差函数的影响,提出了空间距离加角度差异的向量距离模型。以地磁场观测数据作为对象,分别用L1范数、L2范数和新距离模型对数据进行分析,比较3种距离定义下的时空Kriging插值性能。结果表明:加入了角度信息的向量距离,能够更有效地表征数据,提高时空Kriging的插值精度。The spatio-temporal Kriging method can be significantly improved by extending the variogram definition to the space-time domain. The key step in constructing the spatio-temporal variogram is to calculate the vector distances between the time slices and the space slices. This study analyzes the influence of the vector distance on the spatio-temporal variogram construction and presents a vector distance model that includes both the magnitude and the direction information. The algorithm was evaluated using magnetic field data with the evaluations based on the L1 norm and the L2 norm. The results show that the model with the additional direction information in the vector distance, more effectively represented the data characteristics which improved the spatio-temporal Kriging interpolation accuracy.

关 键 词：地磁场 时空Kriging 变差函数 向量角度 

分 类 号：P318.2[天文地球—固体地球物理学]