基于信息扩散的海洋稀疏观测资料插值算法-椭圆模型  

Ellipse model,an algorithm for sparse data interpolation based on information diffusion

作　　者：刘巍[1] 张韧[2] 徐志升[2] 安玉柱[2] 金炜东[1] 

机构地区：[1]西南交通大学信息科学与技术学院,成都610031 [2]解放军理工大学气象学院军事海洋环境军队重点实验室,南京211101

出　　处：《计算力学学报》2012年第6期879-884,共6页Chinese Journal of Computational Mechanics

基　　金：国家自然科学基金(41276088)资助项目

摘　　要：针对海洋科学研究中ARGO等观测资料零散、稀少等问题,提出了一种基于信息扩散思想的插值方法-信息扩散插值算法。该方法基于模糊映射思想,通过对稀少数据点信息进行模糊扩散和插值映射,进而实现有限数据点信息向其邻近区域点的概率插值;针对正态扩散函数在表现非对称结构的数据资料时存在的局限性,发展了一类非均匀信息扩散函数,建立了相应的非均匀信息扩散插值算法-椭圆模型,进行了试验对比和实际ARGO资料的插值应用。Aiming at the difficulties of scattered and sparse observational data in ocean science, a new in- terpolation algorithm based on information diffusion idea was presented in this paper. By fuzzy mapping route,the sparse data samples was diffused and mapped into corresponding fuzzy sets in the form of probability in the interpolation ellipse model. For avoiding the shortcoming of data asymmetrical struc- ture in normal diffusion function,a kind of unsymmetrical information diffusion function was developed, and the corresponding unsymmetrical information diffusion algorithm-ellipse model was established. By making the interpolation experiments and contrast for ARGO sea surface temperature data,the rationali- ty and validity of the ellipse-model were validated.

关 键 词：信息扩散 插值算法 稀疏数据 椭圆模型 

分 类 号：P731.1[天文地球—海洋科学] O241.3[理学—计算数学]