克立格法在时间域上做外延预报的可行性

计算物理 ›› 2006, Vol. 23 ›› Issue (3): 335-342.

克立格法在时间域上做外延预报的可行性

常文渊^1,2, 戴新刚^1,2, 封国林³

1. 中国科学院大气物理研究所, 北京 100029;
2. 兰州大学大气科学院, 甘肃兰州 730000;
3. 扬州大学理学院物理系, 江苏扬州 225009

收稿日期:2004-11-09 修回日期:2005-07-22 出版日期:2006-05-25 发布日期:2006-05-25
作者简介:常文渊(1979-),男,四川成都,博士生,主要从事气候及其预测理论研究.
基金资助:
国家重点基础研究发展规划项目(G1999043400);国家自然科学基金(No.49875024)资助项目

Feasibility of Goestatistical Method on Time Series Forecast

CHANG Wen-yuan^1,2, DAI Xin-gang^1,2, FENG Guo-lin³

1. Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing 100029, China;
2. College of Atmospheric Science, Lanzhou University, Lanzhou 730000, China;
3. Department of Physics, Mathematic and Physics College, Yangzhou University, Yangzhou 225009, China

Received:2004-11-09 Revised:2005-07-22 Online:2006-05-25 Published:2006-05-25

摘要/Abstract

摘要： 利用Lorenz系统混沌解序列和全国160个站的气象资料研究了线性地质统计学在时间域上做外延预报的可行性并与自回归过程AR模型进行比较.结果表明:时间域上普通克立格法(Ordinary Kriging,简称OK)的外延计算虽与矩估计法建模的AR模型法相似,但由于前者使用了无偏性条件使其在平稳或非平稳序列上都具有更好的外延能力;泛克立格法(Universal Kriging,简称UK)由于引入内插中漂移概念反而限制其外延计算,使在平稳序列上的外延解也呈现出类似漂移多项式的变化.同时还提出克立格法有关外延计算的3个试验方案.对实际气象资料的计算表明试验方案存在对OK法外延精度改善的可能性,但这还有赖于外延序列的性质.

关键词: 克立格, AR模型, Lorenz系统, 时间序列

Abstract: To study the feasibility of goestatistical method on time series forecast, we use a section of Lorenz system for extrapolation and try to give a theoretic explanation. Numerical investigation points out that though Ordinary Kriging's(OK) solution resembles that of AR model. OK is better for forecast whether the series is stable or not. Universal Kriging's (UK) results present a drift which deviates from the real value obviously. Three experimental schemes were designed. In a comparison calculation of the ideal datum and meteorological datum, it indicates that the schemes is possible to improve the extrapolation accuracy. It lies on the characteristics of the series and needs further study.

Key words: Kriging, AR model, Lorenz system, time series

中图分类号:

P456.8

常文渊, 戴新刚, 封国林. 克立格法在时间域上做外延预报的可行性[J]. 计算物理, 2006, 23(3): 335-342.

CHANG Wen-yuan, DAI Xin-gang, FENG Guo-lin. Feasibility of Goestatistical Method on Time Series Forecast[J]. CHINESE JOURNAL OF COMPUTATIONAL PHYSICS, 2006, 23(3): 335-342.

[1]	安海岗. 基于复杂网络的时间序列双变量联动波动[J]. 计算物理, 2014, 31(6): 742-750.
[2]	贾蒙. 基于Foliation条件的离散动力系统二维流形计算[J]. 计算物理, 2014, 31(4): 495-504.
[3]	赵贵兵, 石炎福, 段文锋, 余华瑞. 从混沌时间序列同时计算关联维和Kolmogorov熵[J]. 计算物理, 1999, 16(3): 309-315.
[4]	刘健文, 董佩明, 李耀东, 王炳仁, 金维明. 从混沌信号中识别振荡分量的一种算法[J]. 计算物理, 1997, 14(S1): 592-594.
[5]	杨志安, 陈式刚. 动力系统时间延迟重构变换的行为[J]. 计算物理, 1996, 13(3): 315-322.