加权马尔可夫链在农作物年景预测中的应用

The Application of Weighted Markov Chain to the Prediction of Crops Year′s Harvest

首先基于农作物平均年单产量的不确定性、不精确性的特点,利用资料序列的均方差建立农作物丰欠年景的分级标准;然后针对农作物平均年单产量为相依随机变量的特点,采取以规范化的各阶自相关系数为权重,用加权的马尔可夫链模型来预测和分析未来的丰欠年景;最后以西安郊区1980～2002共23年的大白菜平均年单产量资料为实例对该方法进行了具体应用,获得了较为满意的结果,为农作物年景的预测分析提供了一条新的途径.

This paper firstly applied the standard deviation of information series to set up the classification standard of crops year＇s harvest states based on the fact that there are much uncertainty and imprecise characteristics in the crops year＇s harvest course; then this paper presented a method which is called the weighted Markov chain to predict the future year＇s harvest states by regarding the standardized self-coefflcients as weights based on the special characteristics of year＇s harvest being a dependent random variables; and applied this method to a real situation： year＇s harvest oi Chinese cabbage in the suburbs of Xi＇an with the yield per hundred square meter through the year 1980 upto 2002 altogathe 23 years at last. This method provides a new way to predict the year＇s harvest, and the ideal result was obtained.